Commit ·
def945f
0
Parent(s):
Squash history after removing optimizer states
Browse files- .gitattributes +39 -0
- README.md +89 -0
- libero-plus/added_tokens.json +54 -0
- libero-plus/chat_template.jinja +6 -0
- libero-plus/config.json +366 -0
- libero-plus/libero_posttrain_metadata.json +1285 -0
- libero-plus/merges.txt +0 -0
- libero-plus/model.safetensors +3 -0
- libero-plus/special_tokens_map.json +40 -0
- libero-plus/tokenizer.json +3 -0
- libero-plus/tokenizer_config.json +458 -0
- libero-plus/vocab.json +0 -0
- libero/added_tokens.json +54 -0
- libero/chat_template.jinja +6 -0
- libero/config.json +366 -0
- libero/libero_posttrain_metadata.json +1285 -0
- libero/merges.txt +0 -0
- libero/model.safetensors +3 -0
- libero/special_tokens_map.json +40 -0
- libero/tokenizer.json +3 -0
- libero/tokenizer_config.json +458 -0
- libero/vocab.json +0 -0
- pretrained/added_tokens.json +78 -0
- pretrained/chat_template.jinja +6 -0
- pretrained/config.json +366 -0
- pretrained/human_tactile_pretrain_metadata.json +0 -0
- pretrained/merges.txt +0 -0
- pretrained/model.safetensors +3 -0
- pretrained/special_tokens_map.json +40 -0
- pretrained/tokenizer.json +3 -0
- pretrained/tokenizer_config.json +650 -0
- pretrained/vocab.json +0 -0
- robocasa/added_tokens.json +54 -0
- robocasa/chat_template.jinja +6 -0
- robocasa/config.json +366 -0
- robocasa/merges.txt +0 -0
- robocasa/model.safetensors +3 -0
- robocasa/robocasa_human_posttrain_metadata.json +0 -0
- robocasa/special_tokens_map.json +40 -0
- robocasa/tokenizer.json +3 -0
- robocasa/tokenizer_config.json +458 -0
- robocasa/vocab.json +0 -0
.gitattributes
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
libero/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
libero-plus/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
pretrained/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
robocasa/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# TTP: Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation
|
| 2 |
+
|
| 3 |
+
[](https://research.beingbeyond.com/TTP)
|
| 4 |
+
[](https://arxiv.org/pdf/2607.01067)
|
| 5 |
+
[](https://huggingface.co/collections/BeingBeyond/TTP)
|
| 6 |
+
[](./LICENSE)
|
| 7 |
+
|
| 8 |
+
## Model Checkpoints and Datasets
|
| 9 |
+
|
| 10 |
+
Download models from Hugging Face:
|
| 11 |
+
|
| 12 |
+
| Model Type | Model Name | Description |
|
| 13 |
+
|------------|------------|-------------|
|
| 14 |
+
| **VLA Pre-trained** | [TTP-pretrained](https://huggingface.co/BeingBeyond/TTP-pretrained) | Base vision-language-action model (preview) |
|
| 15 |
+
| **VLA Post-trained** | [TTP-LIBERO](https://huggingface.co/BeingBeyond/TTP-LIBERO) | Post-trained on LIBERO benchmark |
|
| 16 |
+
| **VLA Post-trained** | [TTP-LIBERO-plus](https://huggingface.co/BeingBeyond/TTP-LIBERO-plus) | Post-trained on LIBERO, zero-shot evaluated on LIBERO-plus |
|
| 17 |
+
| **VLA Post-trained** | [TTP-RoboCasa](https://huggingface.co/BeingBeyond/TTP-RoboCasa) | Post-trained on RoboCasa 24 tasks |
|
| 18 |
+
|
| 19 |
+
The whole datasets of H-Tac will be coming soon. For now, you can download a small subset of H-Tac from Hugging Face for testing and evaluation: [H-Tac](https://huggingface.co/datasets/BeingBeyond/H-Tac)
|
| 20 |
+
|
| 21 |
+
## Setup
|
| 22 |
+
|
| 23 |
+
### Clone repository
|
| 24 |
+
|
| 25 |
+
```bash
|
| 26 |
+
git clone https://github.com/BeingBeyond/TTP.git
|
| 27 |
+
cd TTP
|
| 28 |
+
```
|
| 29 |
+
|
| 30 |
+
### Create environment
|
| 31 |
+
|
| 32 |
+
```bash
|
| 33 |
+
conda create -n beingh python=3.10
|
| 34 |
+
conda activate beingh
|
| 35 |
+
```
|
| 36 |
+
|
| 37 |
+
### Install package
|
| 38 |
+
|
| 39 |
+
```bash
|
| 40 |
+
pip install -r requirements.txt
|
| 41 |
+
pip install flash-attn --no-build-isolation
|
| 42 |
+
```
|
| 43 |
+
|
| 44 |
+
## Pre-Training
|
| 45 |
+
|
| 46 |
+
```bash
|
| 47 |
+
bash scripts/train/train_human_tactile.sh
|
| 48 |
+
```
|
| 49 |
+
|
| 50 |
+
## Post-Training
|
| 51 |
+
|
| 52 |
+
```bash
|
| 53 |
+
bash scripts/train/train_libero_example.sh
|
| 54 |
+
bash scripts/train/train_robocasa.sh
|
| 55 |
+
```
|
| 56 |
+
|
| 57 |
+
## Evaluation
|
| 58 |
+
|
| 59 |
+
```bash
|
| 60 |
+
bash scripts/eval/eval-libero-fast.sh
|
| 61 |
+
bash scripts/eval/eval-libero-plus.sh
|
| 62 |
+
bash scripts/eval/eval-robocasa-multiprocess.sh
|
| 63 |
+
```
|
| 64 |
+
|
| 65 |
+
## Acknowledgments
|
| 66 |
+
|
| 67 |
+
TTP builds on the following excellent open-source projects:
|
| 68 |
+
|
| 69 |
+
- [InternVL](https://github.com/OpenGVLab/InternVL): Vision-Language model backbone
|
| 70 |
+
- [Bagel](https://github.com/ByteDance-Seed/Bagel): Training framework
|
| 71 |
+
- [Qwen](https://github.com/QwenLM/Qwen): Language model and MoE expert
|
| 72 |
+
- [LIBERO](https://github.com/Lifelong-Robot-Learning/LIBERO): Benchmark for lifelong robot learning
|
| 73 |
+
- [RoboCasa](https://github.com/robocasa/robocasa): Large-scale simulation benchmark for everyday tasks
|
| 74 |
+
- [Being-H0.5](https://github.com/BeingBeyond/Being-H): Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization
|
| 75 |
+
|
| 76 |
+
We thank the authors for their contributions to the robotics and machine learning communities.
|
| 77 |
+
|
| 78 |
+
## Citation
|
| 79 |
+
|
| 80 |
+
If you find this work useful in your research, please consider citing us!
|
| 81 |
+
|
| 82 |
+
```bibtex
|
| 83 |
+
@article{beingbeyond2026ttp,
|
| 84 |
+
title={Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation},
|
| 85 |
+
author={Zhang, Chi and Cai, Penglin and Xi, Ziheng and Yuan, Haoqi and Luo, Hao and Zhang, Wanpeng and Zheng, Sipeng and Xu, Chaoyi and Lu, Zongqing},
|
| 86 |
+
journal={arXiv preprint arXiv:2607.01067},
|
| 87 |
+
year={2026}
|
| 88 |
+
}
|
| 89 |
+
```
|
libero-plus/added_tokens.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</box>": 151677,
|
| 3 |
+
"</img>": 151670,
|
| 4 |
+
"</quad>": 151673,
|
| 5 |
+
"</ref>": 151675,
|
| 6 |
+
"</think>": 151668,
|
| 7 |
+
"</tool_call>": 151658,
|
| 8 |
+
"</tool_response>": 151666,
|
| 9 |
+
"<ACTION_TOKEN_0>": 151687,
|
| 10 |
+
"<ACTION_TOKEN_1>": 151688,
|
| 11 |
+
"<ACTION_TOKEN_2>": 151689,
|
| 12 |
+
"<ACTION_TOKEN_3>": 151690,
|
| 13 |
+
"<ACTION_TOKEN_4>": 151691,
|
| 14 |
+
"<ACTION_TOKEN_5>": 151692,
|
| 15 |
+
"<ACTION_TOKEN_6>": 151693,
|
| 16 |
+
"<ACTION_TOKEN_7>": 151694,
|
| 17 |
+
"<IMG_CONTEXT>": 151671,
|
| 18 |
+
"<PROP_CONTEXT>": 151686,
|
| 19 |
+
"<box>": 151676,
|
| 20 |
+
"<img>": 151669,
|
| 21 |
+
"<quad>": 151672,
|
| 22 |
+
"<ref>": 151674,
|
| 23 |
+
"<think>": 151667,
|
| 24 |
+
"<tool_call>": 151657,
|
| 25 |
+
"<tool_response>": 151665,
|
| 26 |
+
"<vision_end>": 151679,
|
| 27 |
+
"<vision_start>": 151678,
|
| 28 |
+
"<|action_end|>": 151683,
|
| 29 |
+
"<|action_start|>": 151682,
|
| 30 |
+
"<|box_end|>": 151649,
|
| 31 |
+
"<|box_start|>": 151648,
|
| 32 |
+
"<|endoftext|>": 151643,
|
| 33 |
+
"<|file_sep|>": 151664,
|
| 34 |
+
"<|fim_middle|>": 151660,
|
| 35 |
+
"<|fim_pad|>": 151662,
|
| 36 |
+
"<|fim_prefix|>": 151659,
|
| 37 |
+
"<|fim_suffix|>": 151661,
|
| 38 |
+
"<|im_end|>": 151645,
|
| 39 |
+
"<|im_start|>": 151644,
|
| 40 |
+
"<|image_pad|>": 151655,
|
| 41 |
+
"<|object_ref_end|>": 151647,
|
| 42 |
+
"<|object_ref_start|>": 151646,
|
| 43 |
+
"<|quad_end|>": 151651,
|
| 44 |
+
"<|quad_start|>": 151650,
|
| 45 |
+
"<|repo_name|>": 151663,
|
| 46 |
+
"<|state_end|>": 151685,
|
| 47 |
+
"<|state_start|>": 151684,
|
| 48 |
+
"<|tac_end|>": 151681,
|
| 49 |
+
"<|tac_start|>": 151680,
|
| 50 |
+
"<|video_pad|>": 151656,
|
| 51 |
+
"<|vision_end|>": 151653,
|
| 52 |
+
"<|vision_pad|>": 151654,
|
| 53 |
+
"<|vision_start|>": 151652
|
| 54 |
+
}
|
libero-plus/chat_template.jinja
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{{'<|im_start|>' + message['role'] + '
|
| 2 |
+
'}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<image>
|
| 3 |
+
' }}{% elif content['type'] == 'video' %}{{ '<video>
|
| 4 |
+
' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>
|
| 5 |
+
'}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
|
| 6 |
+
' }}{% endif %}
|
libero-plus/config.json
ADDED
|
@@ -0,0 +1,366 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"return_dict": true,
|
| 3 |
+
"output_hidden_states": false,
|
| 4 |
+
"torchscript": false,
|
| 5 |
+
"dtype": null,
|
| 6 |
+
"pruned_heads": {},
|
| 7 |
+
"tie_word_embeddings": true,
|
| 8 |
+
"chunk_size_feed_forward": 0,
|
| 9 |
+
"is_encoder_decoder": false,
|
| 10 |
+
"is_decoder": false,
|
| 11 |
+
"cross_attention_hidden_size": null,
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"tie_encoder_decoder": false,
|
| 14 |
+
"architectures": null,
|
| 15 |
+
"finetuning_task": null,
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "LABEL_0",
|
| 18 |
+
"1": "LABEL_1"
|
| 19 |
+
},
|
| 20 |
+
"label2id": {
|
| 21 |
+
"LABEL_0": 0,
|
| 22 |
+
"LABEL_1": 1
|
| 23 |
+
},
|
| 24 |
+
"task_specific_params": null,
|
| 25 |
+
"problem_type": null,
|
| 26 |
+
"tokenizer_class": null,
|
| 27 |
+
"prefix": null,
|
| 28 |
+
"bos_token_id": null,
|
| 29 |
+
"pad_token_id": null,
|
| 30 |
+
"eos_token_id": null,
|
| 31 |
+
"sep_token_id": null,
|
| 32 |
+
"decoder_start_token_id": null,
|
| 33 |
+
"max_length": 20,
|
| 34 |
+
"min_length": 0,
|
| 35 |
+
"do_sample": false,
|
| 36 |
+
"early_stopping": false,
|
| 37 |
+
"num_beams": 1,
|
| 38 |
+
"temperature": 1.0,
|
| 39 |
+
"top_k": 50,
|
| 40 |
+
"top_p": 1.0,
|
| 41 |
+
"typical_p": 1.0,
|
| 42 |
+
"repetition_penalty": 1.0,
|
| 43 |
+
"length_penalty": 1.0,
|
| 44 |
+
"no_repeat_ngram_size": 0,
|
| 45 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 46 |
+
"bad_words_ids": null,
|
| 47 |
+
"num_return_sequences": 1,
|
| 48 |
+
"output_scores": false,
|
| 49 |
+
"return_dict_in_generate": false,
|
| 50 |
+
"forced_bos_token_id": null,
|
| 51 |
+
"forced_eos_token_id": null,
|
| 52 |
+
"remove_invalid_values": false,
|
| 53 |
+
"exponential_decay_length_penalty": null,
|
| 54 |
+
"suppress_tokens": null,
|
| 55 |
+
"begin_suppress_tokens": null,
|
| 56 |
+
"num_beam_groups": 1,
|
| 57 |
+
"diversity_penalty": 0.0,
|
| 58 |
+
"_name_or_path": "",
|
| 59 |
+
"transformers_version": "4.57.1",
|
| 60 |
+
"use_mpg": false,
|
| 61 |
+
"mpg_num_projections": 32,
|
| 62 |
+
"mpg_lambda": 0.1,
|
| 63 |
+
"mpg_use_stop_gradient": true,
|
| 64 |
+
"mpg_refinement_iters": 1,
|
| 65 |
+
"mpg_gate_temperature": 1.0,
|
| 66 |
+
"use_training_time_rtc": false,
|
| 67 |
+
"simulated_delay": 0,
|
| 68 |
+
"rtc_delay_exp_weight": true,
|
| 69 |
+
"use_inference_prefix_overwrite": true,
|
| 70 |
+
"tf_legacy_loss": false,
|
| 71 |
+
"use_bfloat16": false,
|
| 72 |
+
"llm_config": {
|
| 73 |
+
"vocab_size": 151695,
|
| 74 |
+
"max_position_embeddings": 40960,
|
| 75 |
+
"hidden_size": 2048,
|
| 76 |
+
"intermediate_size": 6144,
|
| 77 |
+
"num_hidden_layers": 28,
|
| 78 |
+
"num_attention_heads": 16,
|
| 79 |
+
"use_sliding_window": false,
|
| 80 |
+
"sliding_window": null,
|
| 81 |
+
"max_window_layers": 28,
|
| 82 |
+
"num_key_value_heads": 8,
|
| 83 |
+
"hidden_act": "silu",
|
| 84 |
+
"initializer_range": 0.02,
|
| 85 |
+
"rms_norm_eps": 1e-06,
|
| 86 |
+
"use_cache": false,
|
| 87 |
+
"rope_theta": 1000000,
|
| 88 |
+
"rope_scaling": null,
|
| 89 |
+
"attention_bias": false,
|
| 90 |
+
"attention_dropout": 0.0,
|
| 91 |
+
"is_causal": true,
|
| 92 |
+
"return_dict": true,
|
| 93 |
+
"output_hidden_states": false,
|
| 94 |
+
"torchscript": false,
|
| 95 |
+
"dtype": "bfloat16",
|
| 96 |
+
"pruned_heads": {},
|
| 97 |
+
"tie_word_embeddings": false,
|
| 98 |
+
"chunk_size_feed_forward": 0,
|
| 99 |
+
"is_encoder_decoder": false,
|
| 100 |
+
"is_decoder": false,
|
| 101 |
+
"cross_attention_hidden_size": null,
|
| 102 |
+
"add_cross_attention": false,
|
| 103 |
+
"tie_encoder_decoder": false,
|
| 104 |
+
"architectures": [
|
| 105 |
+
"Qwen3ForCausalLM"
|
| 106 |
+
],
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"id2label": {
|
| 109 |
+
"0": "LABEL_0",
|
| 110 |
+
"1": "LABEL_1"
|
| 111 |
+
},
|
| 112 |
+
"label2id": {
|
| 113 |
+
"LABEL_0": 0,
|
| 114 |
+
"LABEL_1": 1
|
| 115 |
+
},
|
| 116 |
+
"task_specific_params": null,
|
| 117 |
+
"problem_type": null,
|
| 118 |
+
"tokenizer_class": null,
|
| 119 |
+
"prefix": null,
|
| 120 |
+
"bos_token_id": 151643,
|
| 121 |
+
"pad_token_id": null,
|
| 122 |
+
"eos_token_id": 151645,
|
| 123 |
+
"sep_token_id": null,
|
| 124 |
+
"decoder_start_token_id": null,
|
| 125 |
+
"max_length": 20,
|
| 126 |
+
"min_length": 0,
|
| 127 |
+
"do_sample": false,
|
| 128 |
+
"early_stopping": false,
|
| 129 |
+
"num_beams": 1,
|
| 130 |
+
"temperature": 1.0,
|
| 131 |
+
"top_k": 50,
|
| 132 |
+
"top_p": 1.0,
|
| 133 |
+
"typical_p": 1.0,
|
| 134 |
+
"repetition_penalty": 1.0,
|
| 135 |
+
"length_penalty": 1.0,
|
| 136 |
+
"no_repeat_ngram_size": 0,
|
| 137 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 138 |
+
"bad_words_ids": null,
|
| 139 |
+
"num_return_sequences": 1,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"return_dict_in_generate": false,
|
| 142 |
+
"forced_bos_token_id": null,
|
| 143 |
+
"forced_eos_token_id": null,
|
| 144 |
+
"remove_invalid_values": false,
|
| 145 |
+
"exponential_decay_length_penalty": null,
|
| 146 |
+
"suppress_tokens": null,
|
| 147 |
+
"begin_suppress_tokens": null,
|
| 148 |
+
"num_beam_groups": 1,
|
| 149 |
+
"diversity_penalty": 0.0,
|
| 150 |
+
"_name_or_path": "/root/codespace/checkpoints/Qwen3-1.7B",
|
| 151 |
+
"debug": false,
|
| 152 |
+
"ep_size": 1,
|
| 153 |
+
"head_dim": 128,
|
| 154 |
+
"micro_forward": false,
|
| 155 |
+
"model_type": "qwen3",
|
| 156 |
+
"skip_checkpoint": false,
|
| 157 |
+
"use_deepep": false,
|
| 158 |
+
"tf_legacy_loss": false,
|
| 159 |
+
"use_bfloat16": false,
|
| 160 |
+
"qk_norm": true,
|
| 161 |
+
"layer_module": "Qwen3MoTDecoderLayer",
|
| 162 |
+
"use_mot": true,
|
| 163 |
+
"expert_config": {
|
| 164 |
+
"vocab_size": 151936,
|
| 165 |
+
"max_position_embeddings": 40960,
|
| 166 |
+
"hidden_size": 1024,
|
| 167 |
+
"intermediate_size": 3072,
|
| 168 |
+
"num_hidden_layers": 28,
|
| 169 |
+
"num_attention_heads": 16,
|
| 170 |
+
"use_sliding_window": false,
|
| 171 |
+
"sliding_window": null,
|
| 172 |
+
"max_window_layers": 28,
|
| 173 |
+
"num_key_value_heads": 8,
|
| 174 |
+
"hidden_act": "silu",
|
| 175 |
+
"initializer_range": 0.02,
|
| 176 |
+
"rms_norm_eps": 1e-06,
|
| 177 |
+
"use_cache": true,
|
| 178 |
+
"rope_theta": 1000000,
|
| 179 |
+
"rope_scaling": null,
|
| 180 |
+
"attention_bias": false,
|
| 181 |
+
"attention_dropout": 0.0,
|
| 182 |
+
"is_causal": true,
|
| 183 |
+
"return_dict": true,
|
| 184 |
+
"output_hidden_states": false,
|
| 185 |
+
"torchscript": false,
|
| 186 |
+
"dtype": "bfloat16",
|
| 187 |
+
"pruned_heads": {},
|
| 188 |
+
"tie_word_embeddings": true,
|
| 189 |
+
"chunk_size_feed_forward": 0,
|
| 190 |
+
"is_encoder_decoder": false,
|
| 191 |
+
"is_decoder": false,
|
| 192 |
+
"cross_attention_hidden_size": null,
|
| 193 |
+
"add_cross_attention": false,
|
| 194 |
+
"tie_encoder_decoder": false,
|
| 195 |
+
"architectures": [
|
| 196 |
+
"Qwen3ForCausalLM"
|
| 197 |
+
],
|
| 198 |
+
"finetuning_task": null,
|
| 199 |
+
"id2label": {
|
| 200 |
+
"0": "LABEL_0",
|
| 201 |
+
"1": "LABEL_1"
|
| 202 |
+
},
|
| 203 |
+
"label2id": {
|
| 204 |
+
"LABEL_0": 0,
|
| 205 |
+
"LABEL_1": 1
|
| 206 |
+
},
|
| 207 |
+
"task_specific_params": null,
|
| 208 |
+
"problem_type": null,
|
| 209 |
+
"tokenizer_class": null,
|
| 210 |
+
"prefix": null,
|
| 211 |
+
"bos_token_id": 151643,
|
| 212 |
+
"pad_token_id": null,
|
| 213 |
+
"eos_token_id": 151645,
|
| 214 |
+
"sep_token_id": null,
|
| 215 |
+
"decoder_start_token_id": null,
|
| 216 |
+
"max_length": 20,
|
| 217 |
+
"min_length": 0,
|
| 218 |
+
"do_sample": false,
|
| 219 |
+
"early_stopping": false,
|
| 220 |
+
"num_beams": 1,
|
| 221 |
+
"temperature": 1.0,
|
| 222 |
+
"top_k": 50,
|
| 223 |
+
"top_p": 1.0,
|
| 224 |
+
"typical_p": 1.0,
|
| 225 |
+
"repetition_penalty": 1.0,
|
| 226 |
+
"length_penalty": 1.0,
|
| 227 |
+
"no_repeat_ngram_size": 0,
|
| 228 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 229 |
+
"bad_words_ids": null,
|
| 230 |
+
"num_return_sequences": 1,
|
| 231 |
+
"output_scores": false,
|
| 232 |
+
"return_dict_in_generate": false,
|
| 233 |
+
"forced_bos_token_id": null,
|
| 234 |
+
"forced_eos_token_id": null,
|
| 235 |
+
"remove_invalid_values": false,
|
| 236 |
+
"exponential_decay_length_penalty": null,
|
| 237 |
+
"suppress_tokens": null,
|
| 238 |
+
"begin_suppress_tokens": null,
|
| 239 |
+
"num_beam_groups": 1,
|
| 240 |
+
"diversity_penalty": 0.0,
|
| 241 |
+
"_name_or_path": "",
|
| 242 |
+
"head_dim": 128,
|
| 243 |
+
"model_type": "qwen3",
|
| 244 |
+
"tf_legacy_loss": false,
|
| 245 |
+
"use_bfloat16": false,
|
| 246 |
+
"qk_norm": true,
|
| 247 |
+
"layer_module": "Qwen3DecoderLayer",
|
| 248 |
+
"output_attentions": false
|
| 249 |
+
},
|
| 250 |
+
"attn_implementation": "flash_attention_2",
|
| 251 |
+
"output_attentions": false
|
| 252 |
+
},
|
| 253 |
+
"vit_config": {
|
| 254 |
+
"return_dict": true,
|
| 255 |
+
"output_hidden_states": false,
|
| 256 |
+
"torchscript": false,
|
| 257 |
+
"dtype": "bfloat16",
|
| 258 |
+
"pruned_heads": {},
|
| 259 |
+
"tie_word_embeddings": true,
|
| 260 |
+
"chunk_size_feed_forward": 0,
|
| 261 |
+
"is_encoder_decoder": false,
|
| 262 |
+
"is_decoder": false,
|
| 263 |
+
"cross_attention_hidden_size": null,
|
| 264 |
+
"add_cross_attention": false,
|
| 265 |
+
"tie_encoder_decoder": false,
|
| 266 |
+
"architectures": [
|
| 267 |
+
"InternVisionModel"
|
| 268 |
+
],
|
| 269 |
+
"finetuning_task": null,
|
| 270 |
+
"id2label": {
|
| 271 |
+
"0": "LABEL_0",
|
| 272 |
+
"1": "LABEL_1"
|
| 273 |
+
},
|
| 274 |
+
"label2id": {
|
| 275 |
+
"LABEL_0": 0,
|
| 276 |
+
"LABEL_1": 1
|
| 277 |
+
},
|
| 278 |
+
"task_specific_params": null,
|
| 279 |
+
"problem_type": null,
|
| 280 |
+
"tokenizer_class": null,
|
| 281 |
+
"prefix": null,
|
| 282 |
+
"bos_token_id": null,
|
| 283 |
+
"pad_token_id": null,
|
| 284 |
+
"eos_token_id": null,
|
| 285 |
+
"sep_token_id": null,
|
| 286 |
+
"decoder_start_token_id": null,
|
| 287 |
+
"max_length": 20,
|
| 288 |
+
"min_length": 0,
|
| 289 |
+
"do_sample": false,
|
| 290 |
+
"early_stopping": false,
|
| 291 |
+
"num_beams": 1,
|
| 292 |
+
"temperature": 1.0,
|
| 293 |
+
"top_k": 50,
|
| 294 |
+
"top_p": 1.0,
|
| 295 |
+
"typical_p": 1.0,
|
| 296 |
+
"repetition_penalty": 1.0,
|
| 297 |
+
"length_penalty": 1.0,
|
| 298 |
+
"no_repeat_ngram_size": 0,
|
| 299 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 300 |
+
"bad_words_ids": null,
|
| 301 |
+
"num_return_sequences": 1,
|
| 302 |
+
"output_scores": false,
|
| 303 |
+
"return_dict_in_generate": false,
|
| 304 |
+
"forced_bos_token_id": null,
|
| 305 |
+
"forced_eos_token_id": null,
|
| 306 |
+
"remove_invalid_values": false,
|
| 307 |
+
"exponential_decay_length_penalty": null,
|
| 308 |
+
"suppress_tokens": null,
|
| 309 |
+
"begin_suppress_tokens": null,
|
| 310 |
+
"num_beam_groups": 1,
|
| 311 |
+
"diversity_penalty": 0.0,
|
| 312 |
+
"_name_or_path": "",
|
| 313 |
+
"auto_map": {
|
| 314 |
+
"AutoConfig": "configuration_intern_vit.InternVisionConfig",
|
| 315 |
+
"AutoModel": "modeling_intern_vit.InternVisionModel"
|
| 316 |
+
},
|
| 317 |
+
"model_type": "intern_vit_6b",
|
| 318 |
+
"use_fa3": false,
|
| 319 |
+
"tf_legacy_loss": false,
|
| 320 |
+
"use_bfloat16": false,
|
| 321 |
+
"hidden_size": 1024,
|
| 322 |
+
"intermediate_size": 4096,
|
| 323 |
+
"dropout": 0.0,
|
| 324 |
+
"drop_path_rate": 0.0,
|
| 325 |
+
"num_hidden_layers": 24,
|
| 326 |
+
"num_attention_heads": 16,
|
| 327 |
+
"num_channels": 3,
|
| 328 |
+
"patch_size": 14,
|
| 329 |
+
"image_size": 224,
|
| 330 |
+
"initializer_range": 0.02,
|
| 331 |
+
"initializer_factor": 1.0,
|
| 332 |
+
"attention_dropout": 0.0,
|
| 333 |
+
"layer_norm_eps": 1e-06,
|
| 334 |
+
"hidden_act": "gelu",
|
| 335 |
+
"norm_type": "layer_norm",
|
| 336 |
+
"qkv_bias": true,
|
| 337 |
+
"qk_normalization": false,
|
| 338 |
+
"use_flash_attn": true,
|
| 339 |
+
"select_layer": -1,
|
| 340 |
+
"downsample_ratio": 0.5,
|
| 341 |
+
"output_attentions": false
|
| 342 |
+
},
|
| 343 |
+
"connector_arch": "internvl_connector",
|
| 344 |
+
"template": "being_h0",
|
| 345 |
+
"select_layer": -1,
|
| 346 |
+
"force_image_size": 224,
|
| 347 |
+
"downsample_ratio": 0.5,
|
| 348 |
+
"action_chunk_length": 8,
|
| 349 |
+
"loss_func": "l1",
|
| 350 |
+
"gen_action_type": "prop_hidden",
|
| 351 |
+
"layer_select_for_action": -1,
|
| 352 |
+
"action_token_num": 8,
|
| 353 |
+
"learnable_action_query": false,
|
| 354 |
+
"prompt_template": "long",
|
| 355 |
+
"use_expert": true,
|
| 356 |
+
"use_flow_matching": true,
|
| 357 |
+
"attn_mode": "causal",
|
| 358 |
+
"max_num_embodiments": 32,
|
| 359 |
+
"noise_beta_alpha": 1.5,
|
| 360 |
+
"noise_beta_beta": 1.0,
|
| 361 |
+
"num_timestep_buckets": 1000,
|
| 362 |
+
"noise_s": 0.999,
|
| 363 |
+
"num_inference_timesteps": 4,
|
| 364 |
+
"model_type": "beingh",
|
| 365 |
+
"output_attentions": false
|
| 366 |
+
}
|
libero-plus/libero_posttrain_metadata.json
ADDED
|
@@ -0,0 +1,1285 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"libero_posttrain": {
|
| 3 |
+
"statistics": {
|
| 4 |
+
"state": {
|
| 5 |
+
"eef_rotation": {
|
| 6 |
+
"max": [
|
| 7 |
+
3.6714255809783936,
|
| 8 |
+
3.560650587081909,
|
| 9 |
+
1.386339545249939
|
| 10 |
+
],
|
| 11 |
+
"min": [
|
| 12 |
+
0.35277295112609863,
|
| 13 |
+
-3.641430377960205,
|
| 14 |
+
-1.842738389968872
|
| 15 |
+
],
|
| 16 |
+
"mean": [
|
| 17 |
+
2.9722166336668394,
|
| 18 |
+
-0.2204706193566303,
|
| 19 |
+
-0.12557939087348713
|
| 20 |
+
],
|
| 21 |
+
"std": [
|
| 22 |
+
0.34427400088135357,
|
| 23 |
+
0.9069425374402487,
|
| 24 |
+
0.3253894190906973
|
| 25 |
+
],
|
| 26 |
+
"q01": [
|
| 27 |
+
1.3085840785503386,
|
| 28 |
+
-2.886677579879761,
|
| 29 |
+
-1.1599004411697387
|
| 30 |
+
],
|
| 31 |
+
"q99": [
|
| 32 |
+
3.303542451858519,
|
| 33 |
+
2.7496529006957933,
|
| 34 |
+
0.6893712210655194
|
| 35 |
+
]
|
| 36 |
+
},
|
| 37 |
+
"libero_gripper_position": {
|
| 38 |
+
"max": [
|
| 39 |
+
0.04233968257904053,
|
| 40 |
+
0.0013633022317662835
|
| 41 |
+
],
|
| 42 |
+
"min": [
|
| 43 |
+
-0.0013586411951109767,
|
| 44 |
+
-0.042040832340717316
|
| 45 |
+
],
|
| 46 |
+
"mean": [
|
| 47 |
+
0.02691481335898233,
|
| 48 |
+
-0.02719087286926901
|
| 49 |
+
],
|
| 50 |
+
"std": [
|
| 51 |
+
0.01417594365797819,
|
| 52 |
+
0.014058877749021296
|
| 53 |
+
],
|
| 54 |
+
"q01": [
|
| 55 |
+
0.001503719249740243,
|
| 56 |
+
-0.040336399003863335
|
| 57 |
+
],
|
| 58 |
+
"q99": [
|
| 59 |
+
0.040610933862626555,
|
| 60 |
+
-0.0015016929572448147
|
| 61 |
+
]
|
| 62 |
+
},
|
| 63 |
+
"eef_position": {
|
| 64 |
+
"max": [
|
| 65 |
+
0.21031762659549713,
|
| 66 |
+
0.39128610491752625,
|
| 67 |
+
1.3660105466842651
|
| 68 |
+
],
|
| 69 |
+
"min": [
|
| 70 |
+
-0.4828203022480011,
|
| 71 |
+
-0.3255046010017395,
|
| 72 |
+
0.008128180168569088
|
| 73 |
+
],
|
| 74 |
+
"mean": [
|
| 75 |
+
-0.04651873600711691,
|
| 76 |
+
0.03440890975831591,
|
| 77 |
+
0.764557162431748
|
| 78 |
+
],
|
| 79 |
+
"std": [
|
| 80 |
+
0.1049434680444918,
|
| 81 |
+
0.15176550924794815,
|
| 82 |
+
0.3785180284398934
|
| 83 |
+
],
|
| 84 |
+
"q01": [
|
| 85 |
+
-0.42401049643754957,
|
| 86 |
+
-0.2838300323486328,
|
| 87 |
+
0.009925739830359817
|
| 88 |
+
],
|
| 89 |
+
"q99": [
|
| 90 |
+
0.1530261474847791,
|
| 91 |
+
0.362916499376297,
|
| 92 |
+
1.2910678112506866
|
| 93 |
+
]
|
| 94 |
+
}
|
| 95 |
+
},
|
| 96 |
+
"action": {
|
| 97 |
+
"eef_rotation": {
|
| 98 |
+
"max": [
|
| 99 |
+
0.3557142913341522,
|
| 100 |
+
0.375,
|
| 101 |
+
0.375
|
| 102 |
+
],
|
| 103 |
+
"min": [
|
| 104 |
+
-0.2582142949104309,
|
| 105 |
+
-0.375,
|
| 106 |
+
-0.3675000071525574
|
| 107 |
+
],
|
| 108 |
+
"mean": [
|
| 109 |
+
0.0005407439826102575,
|
| 110 |
+
0.005643430440568553,
|
| 111 |
+
-0.005229132451837535
|
| 112 |
+
],
|
| 113 |
+
"std": [
|
| 114 |
+
0.039242784623089826,
|
| 115 |
+
0.06339272159958631,
|
| 116 |
+
0.077975367145476
|
| 117 |
+
],
|
| 118 |
+
"q01": [
|
| 119 |
+
-0.1510714292526245,
|
| 120 |
+
-0.20678570866584778,
|
| 121 |
+
-0.2742857038974762
|
| 122 |
+
],
|
| 123 |
+
"q99": [
|
| 124 |
+
0.20357142388820648,
|
| 125 |
+
0.26357144117355347,
|
| 126 |
+
0.375
|
| 127 |
+
]
|
| 128 |
+
},
|
| 129 |
+
"gripper_position": {
|
| 130 |
+
"max": [
|
| 131 |
+
1.0
|
| 132 |
+
],
|
| 133 |
+
"min": [
|
| 134 |
+
0.0
|
| 135 |
+
],
|
| 136 |
+
"mean": [
|
| 137 |
+
0.5248203610828128
|
| 138 |
+
],
|
| 139 |
+
"std": [
|
| 140 |
+
0.4994850167690421
|
| 141 |
+
],
|
| 142 |
+
"q01": [
|
| 143 |
+
0.0
|
| 144 |
+
],
|
| 145 |
+
"q99": [
|
| 146 |
+
1.0
|
| 147 |
+
]
|
| 148 |
+
},
|
| 149 |
+
"eef_position": {
|
| 150 |
+
"max": [
|
| 151 |
+
0.9375,
|
| 152 |
+
0.9375,
|
| 153 |
+
0.9375
|
| 154 |
+
],
|
| 155 |
+
"min": [
|
| 156 |
+
-0.9375,
|
| 157 |
+
-0.9375,
|
| 158 |
+
-0.9375
|
| 159 |
+
],
|
| 160 |
+
"mean": [
|
| 161 |
+
0.06278154433021929,
|
| 162 |
+
0.08684070332300477,
|
| 163 |
+
-0.09037311599203464
|
| 164 |
+
],
|
| 165 |
+
"std": [
|
| 166 |
+
0.3355340671542141,
|
| 167 |
+
0.3784624131392225,
|
| 168 |
+
0.44472251877152186
|
| 169 |
+
],
|
| 170 |
+
"q01": [
|
| 171 |
+
-0.8785714507102966,
|
| 172 |
+
-0.8758928775787354,
|
| 173 |
+
-0.9375
|
| 174 |
+
],
|
| 175 |
+
"q99": [
|
| 176 |
+
0.9375,
|
| 177 |
+
0.9107142686843872,
|
| 178 |
+
0.9375
|
| 179 |
+
]
|
| 180 |
+
}
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"modalities": {
|
| 184 |
+
"video": {
|
| 185 |
+
"top_view": {
|
| 186 |
+
"resolution": [
|
| 187 |
+
256,
|
| 188 |
+
256
|
| 189 |
+
],
|
| 190 |
+
"channels": 3,
|
| 191 |
+
"fps": 20.0
|
| 192 |
+
},
|
| 193 |
+
"wrist_view": {
|
| 194 |
+
"resolution": [
|
| 195 |
+
256,
|
| 196 |
+
256
|
| 197 |
+
],
|
| 198 |
+
"channels": 3,
|
| 199 |
+
"fps": 20.0
|
| 200 |
+
}
|
| 201 |
+
},
|
| 202 |
+
"state": {
|
| 203 |
+
"eef_position": {
|
| 204 |
+
"absolute": true,
|
| 205 |
+
"rotation_type": null,
|
| 206 |
+
"shape": [
|
| 207 |
+
3
|
| 208 |
+
],
|
| 209 |
+
"continuous": true
|
| 210 |
+
},
|
| 211 |
+
"eef_rotation": {
|
| 212 |
+
"absolute": true,
|
| 213 |
+
"rotation_type": "axis_angle",
|
| 214 |
+
"shape": [
|
| 215 |
+
3
|
| 216 |
+
],
|
| 217 |
+
"continuous": true
|
| 218 |
+
},
|
| 219 |
+
"libero_gripper_position": {
|
| 220 |
+
"absolute": true,
|
| 221 |
+
"rotation_type": null,
|
| 222 |
+
"shape": [
|
| 223 |
+
2
|
| 224 |
+
],
|
| 225 |
+
"continuous": true
|
| 226 |
+
}
|
| 227 |
+
},
|
| 228 |
+
"action": {
|
| 229 |
+
"eef_position": {
|
| 230 |
+
"absolute": false,
|
| 231 |
+
"rotation_type": null,
|
| 232 |
+
"shape": [
|
| 233 |
+
3
|
| 234 |
+
],
|
| 235 |
+
"continuous": true
|
| 236 |
+
},
|
| 237 |
+
"eef_rotation": {
|
| 238 |
+
"absolute": false,
|
| 239 |
+
"rotation_type": "axis_angle",
|
| 240 |
+
"shape": [
|
| 241 |
+
3
|
| 242 |
+
],
|
| 243 |
+
"continuous": true
|
| 244 |
+
},
|
| 245 |
+
"gripper_position": {
|
| 246 |
+
"absolute": true,
|
| 247 |
+
"rotation_type": null,
|
| 248 |
+
"shape": [
|
| 249 |
+
1
|
| 250 |
+
],
|
| 251 |
+
"continuous": true
|
| 252 |
+
}
|
| 253 |
+
}
|
| 254 |
+
},
|
| 255 |
+
"embodiment_tag": "new_embodiment",
|
| 256 |
+
"default_variant": "libero_spatial_no_noops_1.0.0_lerobot",
|
| 257 |
+
"stats_level": "auto"
|
| 258 |
+
},
|
| 259 |
+
"libero_posttrain_variants": {
|
| 260 |
+
"libero_spatial_no_noops_1.0.0_lerobot": {
|
| 261 |
+
"statistics": {
|
| 262 |
+
"state": {
|
| 263 |
+
"eef_rotation": {
|
| 264 |
+
"max": [
|
| 265 |
+
3.6714255809783936,
|
| 266 |
+
3.560650587081909,
|
| 267 |
+
1.386339545249939
|
| 268 |
+
],
|
| 269 |
+
"min": [
|
| 270 |
+
0.35277295112609863,
|
| 271 |
+
-3.641430377960205,
|
| 272 |
+
-1.842738389968872
|
| 273 |
+
],
|
| 274 |
+
"mean": [
|
| 275 |
+
2.9722166336668394,
|
| 276 |
+
-0.2204706193566303,
|
| 277 |
+
-0.12557939087348713
|
| 278 |
+
],
|
| 279 |
+
"std": [
|
| 280 |
+
0.34427400088135357,
|
| 281 |
+
0.9069425374402487,
|
| 282 |
+
0.3253894190906973
|
| 283 |
+
],
|
| 284 |
+
"q01": [
|
| 285 |
+
1.3085840785503386,
|
| 286 |
+
-2.886677579879761,
|
| 287 |
+
-1.1599004411697387
|
| 288 |
+
],
|
| 289 |
+
"q99": [
|
| 290 |
+
3.303542451858519,
|
| 291 |
+
2.7496529006957933,
|
| 292 |
+
0.6893712210655194
|
| 293 |
+
]
|
| 294 |
+
},
|
| 295 |
+
"libero_gripper_position": {
|
| 296 |
+
"max": [
|
| 297 |
+
0.04233968257904053,
|
| 298 |
+
0.0013633022317662835
|
| 299 |
+
],
|
| 300 |
+
"min": [
|
| 301 |
+
-0.0013586411951109767,
|
| 302 |
+
-0.042040832340717316
|
| 303 |
+
],
|
| 304 |
+
"mean": [
|
| 305 |
+
0.02691481335898233,
|
| 306 |
+
-0.02719087286926901
|
| 307 |
+
],
|
| 308 |
+
"std": [
|
| 309 |
+
0.01417594365797819,
|
| 310 |
+
0.014058877749021296
|
| 311 |
+
],
|
| 312 |
+
"q01": [
|
| 313 |
+
0.001503719249740243,
|
| 314 |
+
-0.040336399003863335
|
| 315 |
+
],
|
| 316 |
+
"q99": [
|
| 317 |
+
0.040610933862626555,
|
| 318 |
+
-0.0015016929572448147
|
| 319 |
+
]
|
| 320 |
+
},
|
| 321 |
+
"eef_position": {
|
| 322 |
+
"max": [
|
| 323 |
+
0.21031762659549713,
|
| 324 |
+
0.39128610491752625,
|
| 325 |
+
1.3660105466842651
|
| 326 |
+
],
|
| 327 |
+
"min": [
|
| 328 |
+
-0.4828203022480011,
|
| 329 |
+
-0.3255046010017395,
|
| 330 |
+
0.008128180168569088
|
| 331 |
+
],
|
| 332 |
+
"mean": [
|
| 333 |
+
-0.04651873600711691,
|
| 334 |
+
0.03440890975831591,
|
| 335 |
+
0.764557162431748
|
| 336 |
+
],
|
| 337 |
+
"std": [
|
| 338 |
+
0.1049434680444918,
|
| 339 |
+
0.15176550924794815,
|
| 340 |
+
0.3785180284398934
|
| 341 |
+
],
|
| 342 |
+
"q01": [
|
| 343 |
+
-0.42401049643754957,
|
| 344 |
+
-0.2838300323486328,
|
| 345 |
+
0.009925739830359817
|
| 346 |
+
],
|
| 347 |
+
"q99": [
|
| 348 |
+
0.1530261474847791,
|
| 349 |
+
0.362916499376297,
|
| 350 |
+
1.2910678112506866
|
| 351 |
+
]
|
| 352 |
+
}
|
| 353 |
+
},
|
| 354 |
+
"action": {
|
| 355 |
+
"eef_rotation": {
|
| 356 |
+
"max": [
|
| 357 |
+
0.3557142913341522,
|
| 358 |
+
0.375,
|
| 359 |
+
0.375
|
| 360 |
+
],
|
| 361 |
+
"min": [
|
| 362 |
+
-0.2582142949104309,
|
| 363 |
+
-0.375,
|
| 364 |
+
-0.3675000071525574
|
| 365 |
+
],
|
| 366 |
+
"mean": [
|
| 367 |
+
0.0005407439826102575,
|
| 368 |
+
0.005643430440568553,
|
| 369 |
+
-0.005229132451837535
|
| 370 |
+
],
|
| 371 |
+
"std": [
|
| 372 |
+
0.039242784623089826,
|
| 373 |
+
0.06339272159958631,
|
| 374 |
+
0.077975367145476
|
| 375 |
+
],
|
| 376 |
+
"q01": [
|
| 377 |
+
-0.1510714292526245,
|
| 378 |
+
-0.20678570866584778,
|
| 379 |
+
-0.2742857038974762
|
| 380 |
+
],
|
| 381 |
+
"q99": [
|
| 382 |
+
0.20357142388820648,
|
| 383 |
+
0.26357144117355347,
|
| 384 |
+
0.375
|
| 385 |
+
]
|
| 386 |
+
},
|
| 387 |
+
"gripper_position": {
|
| 388 |
+
"max": [
|
| 389 |
+
1.0
|
| 390 |
+
],
|
| 391 |
+
"min": [
|
| 392 |
+
0.0
|
| 393 |
+
],
|
| 394 |
+
"mean": [
|
| 395 |
+
0.5248203610828128
|
| 396 |
+
],
|
| 397 |
+
"std": [
|
| 398 |
+
0.4994850167690421
|
| 399 |
+
],
|
| 400 |
+
"q01": [
|
| 401 |
+
0.0
|
| 402 |
+
],
|
| 403 |
+
"q99": [
|
| 404 |
+
1.0
|
| 405 |
+
]
|
| 406 |
+
},
|
| 407 |
+
"eef_position": {
|
| 408 |
+
"max": [
|
| 409 |
+
0.9375,
|
| 410 |
+
0.9375,
|
| 411 |
+
0.9375
|
| 412 |
+
],
|
| 413 |
+
"min": [
|
| 414 |
+
-0.9375,
|
| 415 |
+
-0.9375,
|
| 416 |
+
-0.9375
|
| 417 |
+
],
|
| 418 |
+
"mean": [
|
| 419 |
+
0.06278154433021929,
|
| 420 |
+
0.08684070332300477,
|
| 421 |
+
-0.09037311599203464
|
| 422 |
+
],
|
| 423 |
+
"std": [
|
| 424 |
+
0.3355340671542141,
|
| 425 |
+
0.3784624131392225,
|
| 426 |
+
0.44472251877152186
|
| 427 |
+
],
|
| 428 |
+
"q01": [
|
| 429 |
+
-0.8785714507102966,
|
| 430 |
+
-0.8758928775787354,
|
| 431 |
+
-0.9375
|
| 432 |
+
],
|
| 433 |
+
"q99": [
|
| 434 |
+
0.9375,
|
| 435 |
+
0.9107142686843872,
|
| 436 |
+
0.9375
|
| 437 |
+
]
|
| 438 |
+
}
|
| 439 |
+
}
|
| 440 |
+
},
|
| 441 |
+
"modalities": {
|
| 442 |
+
"video": {
|
| 443 |
+
"top_view": {
|
| 444 |
+
"resolution": [
|
| 445 |
+
256,
|
| 446 |
+
256
|
| 447 |
+
],
|
| 448 |
+
"channels": 3,
|
| 449 |
+
"fps": 20.0
|
| 450 |
+
},
|
| 451 |
+
"wrist_view": {
|
| 452 |
+
"resolution": [
|
| 453 |
+
256,
|
| 454 |
+
256
|
| 455 |
+
],
|
| 456 |
+
"channels": 3,
|
| 457 |
+
"fps": 20.0
|
| 458 |
+
}
|
| 459 |
+
},
|
| 460 |
+
"state": {
|
| 461 |
+
"eef_position": {
|
| 462 |
+
"absolute": true,
|
| 463 |
+
"rotation_type": null,
|
| 464 |
+
"shape": [
|
| 465 |
+
3
|
| 466 |
+
],
|
| 467 |
+
"continuous": true
|
| 468 |
+
},
|
| 469 |
+
"eef_rotation": {
|
| 470 |
+
"absolute": true,
|
| 471 |
+
"rotation_type": "axis_angle",
|
| 472 |
+
"shape": [
|
| 473 |
+
3
|
| 474 |
+
],
|
| 475 |
+
"continuous": true
|
| 476 |
+
},
|
| 477 |
+
"libero_gripper_position": {
|
| 478 |
+
"absolute": true,
|
| 479 |
+
"rotation_type": null,
|
| 480 |
+
"shape": [
|
| 481 |
+
2
|
| 482 |
+
],
|
| 483 |
+
"continuous": true
|
| 484 |
+
}
|
| 485 |
+
},
|
| 486 |
+
"action": {
|
| 487 |
+
"eef_position": {
|
| 488 |
+
"absolute": false,
|
| 489 |
+
"rotation_type": null,
|
| 490 |
+
"shape": [
|
| 491 |
+
3
|
| 492 |
+
],
|
| 493 |
+
"continuous": true
|
| 494 |
+
},
|
| 495 |
+
"eef_rotation": {
|
| 496 |
+
"absolute": false,
|
| 497 |
+
"rotation_type": "axis_angle",
|
| 498 |
+
"shape": [
|
| 499 |
+
3
|
| 500 |
+
],
|
| 501 |
+
"continuous": true
|
| 502 |
+
},
|
| 503 |
+
"gripper_position": {
|
| 504 |
+
"absolute": true,
|
| 505 |
+
"rotation_type": null,
|
| 506 |
+
"shape": [
|
| 507 |
+
1
|
| 508 |
+
],
|
| 509 |
+
"continuous": true
|
| 510 |
+
}
|
| 511 |
+
}
|
| 512 |
+
},
|
| 513 |
+
"embodiment_tag": "new_embodiment",
|
| 514 |
+
"stats_level": "task"
|
| 515 |
+
},
|
| 516 |
+
"libero_object_no_noops_1.0.0_lerobot": {
|
| 517 |
+
"statistics": {
|
| 518 |
+
"state": {
|
| 519 |
+
"eef_rotation": {
|
| 520 |
+
"max": [
|
| 521 |
+
3.6714255809783936,
|
| 522 |
+
3.560650587081909,
|
| 523 |
+
1.386339545249939
|
| 524 |
+
],
|
| 525 |
+
"min": [
|
| 526 |
+
0.35277295112609863,
|
| 527 |
+
-3.641430377960205,
|
| 528 |
+
-1.842738389968872
|
| 529 |
+
],
|
| 530 |
+
"mean": [
|
| 531 |
+
2.9722166336668394,
|
| 532 |
+
-0.2204706193566303,
|
| 533 |
+
-0.12557939087348713
|
| 534 |
+
],
|
| 535 |
+
"std": [
|
| 536 |
+
0.34427400088135357,
|
| 537 |
+
0.9069425374402487,
|
| 538 |
+
0.3253894190906973
|
| 539 |
+
],
|
| 540 |
+
"q01": [
|
| 541 |
+
1.3085840785503386,
|
| 542 |
+
-2.886677579879761,
|
| 543 |
+
-1.1599004411697387
|
| 544 |
+
],
|
| 545 |
+
"q99": [
|
| 546 |
+
3.303542451858519,
|
| 547 |
+
2.7496529006957933,
|
| 548 |
+
0.6893712210655194
|
| 549 |
+
]
|
| 550 |
+
},
|
| 551 |
+
"libero_gripper_position": {
|
| 552 |
+
"max": [
|
| 553 |
+
0.04233968257904053,
|
| 554 |
+
0.0013633022317662835
|
| 555 |
+
],
|
| 556 |
+
"min": [
|
| 557 |
+
-0.0013586411951109767,
|
| 558 |
+
-0.042040832340717316
|
| 559 |
+
],
|
| 560 |
+
"mean": [
|
| 561 |
+
0.02691481335898233,
|
| 562 |
+
-0.02719087286926901
|
| 563 |
+
],
|
| 564 |
+
"std": [
|
| 565 |
+
0.01417594365797819,
|
| 566 |
+
0.014058877749021296
|
| 567 |
+
],
|
| 568 |
+
"q01": [
|
| 569 |
+
0.001503719249740243,
|
| 570 |
+
-0.040336399003863335
|
| 571 |
+
],
|
| 572 |
+
"q99": [
|
| 573 |
+
0.040610933862626555,
|
| 574 |
+
-0.0015016929572448147
|
| 575 |
+
]
|
| 576 |
+
},
|
| 577 |
+
"eef_position": {
|
| 578 |
+
"max": [
|
| 579 |
+
0.21031762659549713,
|
| 580 |
+
0.39128610491752625,
|
| 581 |
+
1.3660105466842651
|
| 582 |
+
],
|
| 583 |
+
"min": [
|
| 584 |
+
-0.4828203022480011,
|
| 585 |
+
-0.3255046010017395,
|
| 586 |
+
0.008128180168569088
|
| 587 |
+
],
|
| 588 |
+
"mean": [
|
| 589 |
+
-0.04651873600711691,
|
| 590 |
+
0.03440890975831591,
|
| 591 |
+
0.764557162431748
|
| 592 |
+
],
|
| 593 |
+
"std": [
|
| 594 |
+
0.1049434680444918,
|
| 595 |
+
0.15176550924794815,
|
| 596 |
+
0.3785180284398934
|
| 597 |
+
],
|
| 598 |
+
"q01": [
|
| 599 |
+
-0.42401049643754957,
|
| 600 |
+
-0.2838300323486328,
|
| 601 |
+
0.009925739830359817
|
| 602 |
+
],
|
| 603 |
+
"q99": [
|
| 604 |
+
0.1530261474847791,
|
| 605 |
+
0.362916499376297,
|
| 606 |
+
1.2910678112506866
|
| 607 |
+
]
|
| 608 |
+
}
|
| 609 |
+
},
|
| 610 |
+
"action": {
|
| 611 |
+
"eef_rotation": {
|
| 612 |
+
"max": [
|
| 613 |
+
0.3557142913341522,
|
| 614 |
+
0.375,
|
| 615 |
+
0.375
|
| 616 |
+
],
|
| 617 |
+
"min": [
|
| 618 |
+
-0.2582142949104309,
|
| 619 |
+
-0.375,
|
| 620 |
+
-0.3675000071525574
|
| 621 |
+
],
|
| 622 |
+
"mean": [
|
| 623 |
+
0.0005407439826102575,
|
| 624 |
+
0.005643430440568553,
|
| 625 |
+
-0.005229132451837535
|
| 626 |
+
],
|
| 627 |
+
"std": [
|
| 628 |
+
0.039242784623089826,
|
| 629 |
+
0.06339272159958631,
|
| 630 |
+
0.077975367145476
|
| 631 |
+
],
|
| 632 |
+
"q01": [
|
| 633 |
+
-0.1510714292526245,
|
| 634 |
+
-0.20678570866584778,
|
| 635 |
+
-0.2742857038974762
|
| 636 |
+
],
|
| 637 |
+
"q99": [
|
| 638 |
+
0.20357142388820648,
|
| 639 |
+
0.26357144117355347,
|
| 640 |
+
0.375
|
| 641 |
+
]
|
| 642 |
+
},
|
| 643 |
+
"gripper_position": {
|
| 644 |
+
"max": [
|
| 645 |
+
1.0
|
| 646 |
+
],
|
| 647 |
+
"min": [
|
| 648 |
+
0.0
|
| 649 |
+
],
|
| 650 |
+
"mean": [
|
| 651 |
+
0.5248203610828128
|
| 652 |
+
],
|
| 653 |
+
"std": [
|
| 654 |
+
0.4994850167690421
|
| 655 |
+
],
|
| 656 |
+
"q01": [
|
| 657 |
+
0.0
|
| 658 |
+
],
|
| 659 |
+
"q99": [
|
| 660 |
+
1.0
|
| 661 |
+
]
|
| 662 |
+
},
|
| 663 |
+
"eef_position": {
|
| 664 |
+
"max": [
|
| 665 |
+
0.9375,
|
| 666 |
+
0.9375,
|
| 667 |
+
0.9375
|
| 668 |
+
],
|
| 669 |
+
"min": [
|
| 670 |
+
-0.9375,
|
| 671 |
+
-0.9375,
|
| 672 |
+
-0.9375
|
| 673 |
+
],
|
| 674 |
+
"mean": [
|
| 675 |
+
0.06278154433021929,
|
| 676 |
+
0.08684070332300477,
|
| 677 |
+
-0.09037311599203464
|
| 678 |
+
],
|
| 679 |
+
"std": [
|
| 680 |
+
0.3355340671542141,
|
| 681 |
+
0.3784624131392225,
|
| 682 |
+
0.44472251877152186
|
| 683 |
+
],
|
| 684 |
+
"q01": [
|
| 685 |
+
-0.8785714507102966,
|
| 686 |
+
-0.8758928775787354,
|
| 687 |
+
-0.9375
|
| 688 |
+
],
|
| 689 |
+
"q99": [
|
| 690 |
+
0.9375,
|
| 691 |
+
0.9107142686843872,
|
| 692 |
+
0.9375
|
| 693 |
+
]
|
| 694 |
+
}
|
| 695 |
+
}
|
| 696 |
+
},
|
| 697 |
+
"modalities": {
|
| 698 |
+
"video": {
|
| 699 |
+
"top_view": {
|
| 700 |
+
"resolution": [
|
| 701 |
+
256,
|
| 702 |
+
256
|
| 703 |
+
],
|
| 704 |
+
"channels": 3,
|
| 705 |
+
"fps": 20.0
|
| 706 |
+
},
|
| 707 |
+
"wrist_view": {
|
| 708 |
+
"resolution": [
|
| 709 |
+
256,
|
| 710 |
+
256
|
| 711 |
+
],
|
| 712 |
+
"channels": 3,
|
| 713 |
+
"fps": 20.0
|
| 714 |
+
}
|
| 715 |
+
},
|
| 716 |
+
"state": {
|
| 717 |
+
"eef_position": {
|
| 718 |
+
"absolute": true,
|
| 719 |
+
"rotation_type": null,
|
| 720 |
+
"shape": [
|
| 721 |
+
3
|
| 722 |
+
],
|
| 723 |
+
"continuous": true
|
| 724 |
+
},
|
| 725 |
+
"eef_rotation": {
|
| 726 |
+
"absolute": true,
|
| 727 |
+
"rotation_type": "axis_angle",
|
| 728 |
+
"shape": [
|
| 729 |
+
3
|
| 730 |
+
],
|
| 731 |
+
"continuous": true
|
| 732 |
+
},
|
| 733 |
+
"libero_gripper_position": {
|
| 734 |
+
"absolute": true,
|
| 735 |
+
"rotation_type": null,
|
| 736 |
+
"shape": [
|
| 737 |
+
2
|
| 738 |
+
],
|
| 739 |
+
"continuous": true
|
| 740 |
+
}
|
| 741 |
+
},
|
| 742 |
+
"action": {
|
| 743 |
+
"eef_position": {
|
| 744 |
+
"absolute": false,
|
| 745 |
+
"rotation_type": null,
|
| 746 |
+
"shape": [
|
| 747 |
+
3
|
| 748 |
+
],
|
| 749 |
+
"continuous": true
|
| 750 |
+
},
|
| 751 |
+
"eef_rotation": {
|
| 752 |
+
"absolute": false,
|
| 753 |
+
"rotation_type": "axis_angle",
|
| 754 |
+
"shape": [
|
| 755 |
+
3
|
| 756 |
+
],
|
| 757 |
+
"continuous": true
|
| 758 |
+
},
|
| 759 |
+
"gripper_position": {
|
| 760 |
+
"absolute": true,
|
| 761 |
+
"rotation_type": null,
|
| 762 |
+
"shape": [
|
| 763 |
+
1
|
| 764 |
+
],
|
| 765 |
+
"continuous": true
|
| 766 |
+
}
|
| 767 |
+
}
|
| 768 |
+
},
|
| 769 |
+
"embodiment_tag": "new_embodiment",
|
| 770 |
+
"stats_level": "task"
|
| 771 |
+
},
|
| 772 |
+
"libero_goal_no_noops_1.0.0_lerobot": {
|
| 773 |
+
"statistics": {
|
| 774 |
+
"state": {
|
| 775 |
+
"eef_rotation": {
|
| 776 |
+
"max": [
|
| 777 |
+
3.6714255809783936,
|
| 778 |
+
3.560650587081909,
|
| 779 |
+
1.386339545249939
|
| 780 |
+
],
|
| 781 |
+
"min": [
|
| 782 |
+
0.35277295112609863,
|
| 783 |
+
-3.641430377960205,
|
| 784 |
+
-1.842738389968872
|
| 785 |
+
],
|
| 786 |
+
"mean": [
|
| 787 |
+
2.9722166336668394,
|
| 788 |
+
-0.2204706193566303,
|
| 789 |
+
-0.12557939087348713
|
| 790 |
+
],
|
| 791 |
+
"std": [
|
| 792 |
+
0.34427400088135357,
|
| 793 |
+
0.9069425374402487,
|
| 794 |
+
0.3253894190906973
|
| 795 |
+
],
|
| 796 |
+
"q01": [
|
| 797 |
+
1.3085840785503386,
|
| 798 |
+
-2.886677579879761,
|
| 799 |
+
-1.1599004411697387
|
| 800 |
+
],
|
| 801 |
+
"q99": [
|
| 802 |
+
3.303542451858519,
|
| 803 |
+
2.7496529006957933,
|
| 804 |
+
0.6893712210655194
|
| 805 |
+
]
|
| 806 |
+
},
|
| 807 |
+
"libero_gripper_position": {
|
| 808 |
+
"max": [
|
| 809 |
+
0.04233968257904053,
|
| 810 |
+
0.0013633022317662835
|
| 811 |
+
],
|
| 812 |
+
"min": [
|
| 813 |
+
-0.0013586411951109767,
|
| 814 |
+
-0.042040832340717316
|
| 815 |
+
],
|
| 816 |
+
"mean": [
|
| 817 |
+
0.02691481335898233,
|
| 818 |
+
-0.02719087286926901
|
| 819 |
+
],
|
| 820 |
+
"std": [
|
| 821 |
+
0.01417594365797819,
|
| 822 |
+
0.014058877749021296
|
| 823 |
+
],
|
| 824 |
+
"q01": [
|
| 825 |
+
0.001503719249740243,
|
| 826 |
+
-0.040336399003863335
|
| 827 |
+
],
|
| 828 |
+
"q99": [
|
| 829 |
+
0.040610933862626555,
|
| 830 |
+
-0.0015016929572448147
|
| 831 |
+
]
|
| 832 |
+
},
|
| 833 |
+
"eef_position": {
|
| 834 |
+
"max": [
|
| 835 |
+
0.21031762659549713,
|
| 836 |
+
0.39128610491752625,
|
| 837 |
+
1.3660105466842651
|
| 838 |
+
],
|
| 839 |
+
"min": [
|
| 840 |
+
-0.4828203022480011,
|
| 841 |
+
-0.3255046010017395,
|
| 842 |
+
0.008128180168569088
|
| 843 |
+
],
|
| 844 |
+
"mean": [
|
| 845 |
+
-0.04651873600711691,
|
| 846 |
+
0.03440890975831591,
|
| 847 |
+
0.764557162431748
|
| 848 |
+
],
|
| 849 |
+
"std": [
|
| 850 |
+
0.1049434680444918,
|
| 851 |
+
0.15176550924794815,
|
| 852 |
+
0.3785180284398934
|
| 853 |
+
],
|
| 854 |
+
"q01": [
|
| 855 |
+
-0.42401049643754957,
|
| 856 |
+
-0.2838300323486328,
|
| 857 |
+
0.009925739830359817
|
| 858 |
+
],
|
| 859 |
+
"q99": [
|
| 860 |
+
0.1530261474847791,
|
| 861 |
+
0.362916499376297,
|
| 862 |
+
1.2910678112506866
|
| 863 |
+
]
|
| 864 |
+
}
|
| 865 |
+
},
|
| 866 |
+
"action": {
|
| 867 |
+
"eef_rotation": {
|
| 868 |
+
"max": [
|
| 869 |
+
0.3557142913341522,
|
| 870 |
+
0.375,
|
| 871 |
+
0.375
|
| 872 |
+
],
|
| 873 |
+
"min": [
|
| 874 |
+
-0.2582142949104309,
|
| 875 |
+
-0.375,
|
| 876 |
+
-0.3675000071525574
|
| 877 |
+
],
|
| 878 |
+
"mean": [
|
| 879 |
+
0.0005407439826102575,
|
| 880 |
+
0.005643430440568553,
|
| 881 |
+
-0.005229132451837535
|
| 882 |
+
],
|
| 883 |
+
"std": [
|
| 884 |
+
0.039242784623089826,
|
| 885 |
+
0.06339272159958631,
|
| 886 |
+
0.077975367145476
|
| 887 |
+
],
|
| 888 |
+
"q01": [
|
| 889 |
+
-0.1510714292526245,
|
| 890 |
+
-0.20678570866584778,
|
| 891 |
+
-0.2742857038974762
|
| 892 |
+
],
|
| 893 |
+
"q99": [
|
| 894 |
+
0.20357142388820648,
|
| 895 |
+
0.26357144117355347,
|
| 896 |
+
0.375
|
| 897 |
+
]
|
| 898 |
+
},
|
| 899 |
+
"gripper_position": {
|
| 900 |
+
"max": [
|
| 901 |
+
1.0
|
| 902 |
+
],
|
| 903 |
+
"min": [
|
| 904 |
+
0.0
|
| 905 |
+
],
|
| 906 |
+
"mean": [
|
| 907 |
+
0.5248203610828128
|
| 908 |
+
],
|
| 909 |
+
"std": [
|
| 910 |
+
0.4994850167690421
|
| 911 |
+
],
|
| 912 |
+
"q01": [
|
| 913 |
+
0.0
|
| 914 |
+
],
|
| 915 |
+
"q99": [
|
| 916 |
+
1.0
|
| 917 |
+
]
|
| 918 |
+
},
|
| 919 |
+
"eef_position": {
|
| 920 |
+
"max": [
|
| 921 |
+
0.9375,
|
| 922 |
+
0.9375,
|
| 923 |
+
0.9375
|
| 924 |
+
],
|
| 925 |
+
"min": [
|
| 926 |
+
-0.9375,
|
| 927 |
+
-0.9375,
|
| 928 |
+
-0.9375
|
| 929 |
+
],
|
| 930 |
+
"mean": [
|
| 931 |
+
0.06278154433021929,
|
| 932 |
+
0.08684070332300477,
|
| 933 |
+
-0.09037311599203464
|
| 934 |
+
],
|
| 935 |
+
"std": [
|
| 936 |
+
0.3355340671542141,
|
| 937 |
+
0.3784624131392225,
|
| 938 |
+
0.44472251877152186
|
| 939 |
+
],
|
| 940 |
+
"q01": [
|
| 941 |
+
-0.8785714507102966,
|
| 942 |
+
-0.8758928775787354,
|
| 943 |
+
-0.9375
|
| 944 |
+
],
|
| 945 |
+
"q99": [
|
| 946 |
+
0.9375,
|
| 947 |
+
0.9107142686843872,
|
| 948 |
+
0.9375
|
| 949 |
+
]
|
| 950 |
+
}
|
| 951 |
+
}
|
| 952 |
+
},
|
| 953 |
+
"modalities": {
|
| 954 |
+
"video": {
|
| 955 |
+
"top_view": {
|
| 956 |
+
"resolution": [
|
| 957 |
+
256,
|
| 958 |
+
256
|
| 959 |
+
],
|
| 960 |
+
"channels": 3,
|
| 961 |
+
"fps": 20.0
|
| 962 |
+
},
|
| 963 |
+
"wrist_view": {
|
| 964 |
+
"resolution": [
|
| 965 |
+
256,
|
| 966 |
+
256
|
| 967 |
+
],
|
| 968 |
+
"channels": 3,
|
| 969 |
+
"fps": 20.0
|
| 970 |
+
}
|
| 971 |
+
},
|
| 972 |
+
"state": {
|
| 973 |
+
"eef_position": {
|
| 974 |
+
"absolute": true,
|
| 975 |
+
"rotation_type": null,
|
| 976 |
+
"shape": [
|
| 977 |
+
3
|
| 978 |
+
],
|
| 979 |
+
"continuous": true
|
| 980 |
+
},
|
| 981 |
+
"eef_rotation": {
|
| 982 |
+
"absolute": true,
|
| 983 |
+
"rotation_type": "axis_angle",
|
| 984 |
+
"shape": [
|
| 985 |
+
3
|
| 986 |
+
],
|
| 987 |
+
"continuous": true
|
| 988 |
+
},
|
| 989 |
+
"libero_gripper_position": {
|
| 990 |
+
"absolute": true,
|
| 991 |
+
"rotation_type": null,
|
| 992 |
+
"shape": [
|
| 993 |
+
2
|
| 994 |
+
],
|
| 995 |
+
"continuous": true
|
| 996 |
+
}
|
| 997 |
+
},
|
| 998 |
+
"action": {
|
| 999 |
+
"eef_position": {
|
| 1000 |
+
"absolute": false,
|
| 1001 |
+
"rotation_type": null,
|
| 1002 |
+
"shape": [
|
| 1003 |
+
3
|
| 1004 |
+
],
|
| 1005 |
+
"continuous": true
|
| 1006 |
+
},
|
| 1007 |
+
"eef_rotation": {
|
| 1008 |
+
"absolute": false,
|
| 1009 |
+
"rotation_type": "axis_angle",
|
| 1010 |
+
"shape": [
|
| 1011 |
+
3
|
| 1012 |
+
],
|
| 1013 |
+
"continuous": true
|
| 1014 |
+
},
|
| 1015 |
+
"gripper_position": {
|
| 1016 |
+
"absolute": true,
|
| 1017 |
+
"rotation_type": null,
|
| 1018 |
+
"shape": [
|
| 1019 |
+
1
|
| 1020 |
+
],
|
| 1021 |
+
"continuous": true
|
| 1022 |
+
}
|
| 1023 |
+
}
|
| 1024 |
+
},
|
| 1025 |
+
"embodiment_tag": "new_embodiment",
|
| 1026 |
+
"stats_level": "task"
|
| 1027 |
+
},
|
| 1028 |
+
"libero_10_no_noops_1.0.0_lerobot": {
|
| 1029 |
+
"statistics": {
|
| 1030 |
+
"state": {
|
| 1031 |
+
"eef_rotation": {
|
| 1032 |
+
"max": [
|
| 1033 |
+
3.6714255809783936,
|
| 1034 |
+
3.560650587081909,
|
| 1035 |
+
1.386339545249939
|
| 1036 |
+
],
|
| 1037 |
+
"min": [
|
| 1038 |
+
0.35277295112609863,
|
| 1039 |
+
-3.641430377960205,
|
| 1040 |
+
-1.842738389968872
|
| 1041 |
+
],
|
| 1042 |
+
"mean": [
|
| 1043 |
+
2.9722166336668394,
|
| 1044 |
+
-0.2204706193566303,
|
| 1045 |
+
-0.12557939087348713
|
| 1046 |
+
],
|
| 1047 |
+
"std": [
|
| 1048 |
+
0.34427400088135357,
|
| 1049 |
+
0.9069425374402487,
|
| 1050 |
+
0.3253894190906973
|
| 1051 |
+
],
|
| 1052 |
+
"q01": [
|
| 1053 |
+
1.3085840785503386,
|
| 1054 |
+
-2.886677579879761,
|
| 1055 |
+
-1.1599004411697387
|
| 1056 |
+
],
|
| 1057 |
+
"q99": [
|
| 1058 |
+
3.303542451858519,
|
| 1059 |
+
2.7496529006957933,
|
| 1060 |
+
0.6893712210655194
|
| 1061 |
+
]
|
| 1062 |
+
},
|
| 1063 |
+
"libero_gripper_position": {
|
| 1064 |
+
"max": [
|
| 1065 |
+
0.04233968257904053,
|
| 1066 |
+
0.0013633022317662835
|
| 1067 |
+
],
|
| 1068 |
+
"min": [
|
| 1069 |
+
-0.0013586411951109767,
|
| 1070 |
+
-0.042040832340717316
|
| 1071 |
+
],
|
| 1072 |
+
"mean": [
|
| 1073 |
+
0.02691481335898233,
|
| 1074 |
+
-0.02719087286926901
|
| 1075 |
+
],
|
| 1076 |
+
"std": [
|
| 1077 |
+
0.01417594365797819,
|
| 1078 |
+
0.014058877749021296
|
| 1079 |
+
],
|
| 1080 |
+
"q01": [
|
| 1081 |
+
0.001503719249740243,
|
| 1082 |
+
-0.040336399003863335
|
| 1083 |
+
],
|
| 1084 |
+
"q99": [
|
| 1085 |
+
0.040610933862626555,
|
| 1086 |
+
-0.0015016929572448147
|
| 1087 |
+
]
|
| 1088 |
+
},
|
| 1089 |
+
"eef_position": {
|
| 1090 |
+
"max": [
|
| 1091 |
+
0.21031762659549713,
|
| 1092 |
+
0.39128610491752625,
|
| 1093 |
+
1.3660105466842651
|
| 1094 |
+
],
|
| 1095 |
+
"min": [
|
| 1096 |
+
-0.4828203022480011,
|
| 1097 |
+
-0.3255046010017395,
|
| 1098 |
+
0.008128180168569088
|
| 1099 |
+
],
|
| 1100 |
+
"mean": [
|
| 1101 |
+
-0.04651873600711691,
|
| 1102 |
+
0.03440890975831591,
|
| 1103 |
+
0.764557162431748
|
| 1104 |
+
],
|
| 1105 |
+
"std": [
|
| 1106 |
+
0.1049434680444918,
|
| 1107 |
+
0.15176550924794815,
|
| 1108 |
+
0.3785180284398934
|
| 1109 |
+
],
|
| 1110 |
+
"q01": [
|
| 1111 |
+
-0.42401049643754957,
|
| 1112 |
+
-0.2838300323486328,
|
| 1113 |
+
0.009925739830359817
|
| 1114 |
+
],
|
| 1115 |
+
"q99": [
|
| 1116 |
+
0.1530261474847791,
|
| 1117 |
+
0.362916499376297,
|
| 1118 |
+
1.2910678112506866
|
| 1119 |
+
]
|
| 1120 |
+
}
|
| 1121 |
+
},
|
| 1122 |
+
"action": {
|
| 1123 |
+
"eef_rotation": {
|
| 1124 |
+
"max": [
|
| 1125 |
+
0.3557142913341522,
|
| 1126 |
+
0.375,
|
| 1127 |
+
0.375
|
| 1128 |
+
],
|
| 1129 |
+
"min": [
|
| 1130 |
+
-0.2582142949104309,
|
| 1131 |
+
-0.375,
|
| 1132 |
+
-0.3675000071525574
|
| 1133 |
+
],
|
| 1134 |
+
"mean": [
|
| 1135 |
+
0.0005407439826102575,
|
| 1136 |
+
0.005643430440568553,
|
| 1137 |
+
-0.005229132451837535
|
| 1138 |
+
],
|
| 1139 |
+
"std": [
|
| 1140 |
+
0.039242784623089826,
|
| 1141 |
+
0.06339272159958631,
|
| 1142 |
+
0.077975367145476
|
| 1143 |
+
],
|
| 1144 |
+
"q01": [
|
| 1145 |
+
-0.1510714292526245,
|
| 1146 |
+
-0.20678570866584778,
|
| 1147 |
+
-0.2742857038974762
|
| 1148 |
+
],
|
| 1149 |
+
"q99": [
|
| 1150 |
+
0.20357142388820648,
|
| 1151 |
+
0.26357144117355347,
|
| 1152 |
+
0.375
|
| 1153 |
+
]
|
| 1154 |
+
},
|
| 1155 |
+
"gripper_position": {
|
| 1156 |
+
"max": [
|
| 1157 |
+
1.0
|
| 1158 |
+
],
|
| 1159 |
+
"min": [
|
| 1160 |
+
0.0
|
| 1161 |
+
],
|
| 1162 |
+
"mean": [
|
| 1163 |
+
0.5248203610828128
|
| 1164 |
+
],
|
| 1165 |
+
"std": [
|
| 1166 |
+
0.4994850167690421
|
| 1167 |
+
],
|
| 1168 |
+
"q01": [
|
| 1169 |
+
0.0
|
| 1170 |
+
],
|
| 1171 |
+
"q99": [
|
| 1172 |
+
1.0
|
| 1173 |
+
]
|
| 1174 |
+
},
|
| 1175 |
+
"eef_position": {
|
| 1176 |
+
"max": [
|
| 1177 |
+
0.9375,
|
| 1178 |
+
0.9375,
|
| 1179 |
+
0.9375
|
| 1180 |
+
],
|
| 1181 |
+
"min": [
|
| 1182 |
+
-0.9375,
|
| 1183 |
+
-0.9375,
|
| 1184 |
+
-0.9375
|
| 1185 |
+
],
|
| 1186 |
+
"mean": [
|
| 1187 |
+
0.06278154433021929,
|
| 1188 |
+
0.08684070332300477,
|
| 1189 |
+
-0.09037311599203464
|
| 1190 |
+
],
|
| 1191 |
+
"std": [
|
| 1192 |
+
0.3355340671542141,
|
| 1193 |
+
0.3784624131392225,
|
| 1194 |
+
0.44472251877152186
|
| 1195 |
+
],
|
| 1196 |
+
"q01": [
|
| 1197 |
+
-0.8785714507102966,
|
| 1198 |
+
-0.8758928775787354,
|
| 1199 |
+
-0.9375
|
| 1200 |
+
],
|
| 1201 |
+
"q99": [
|
| 1202 |
+
0.9375,
|
| 1203 |
+
0.9107142686843872,
|
| 1204 |
+
0.9375
|
| 1205 |
+
]
|
| 1206 |
+
}
|
| 1207 |
+
}
|
| 1208 |
+
},
|
| 1209 |
+
"modalities": {
|
| 1210 |
+
"video": {
|
| 1211 |
+
"top_view": {
|
| 1212 |
+
"resolution": [
|
| 1213 |
+
256,
|
| 1214 |
+
256
|
| 1215 |
+
],
|
| 1216 |
+
"channels": 3,
|
| 1217 |
+
"fps": 20.0
|
| 1218 |
+
},
|
| 1219 |
+
"wrist_view": {
|
| 1220 |
+
"resolution": [
|
| 1221 |
+
256,
|
| 1222 |
+
256
|
| 1223 |
+
],
|
| 1224 |
+
"channels": 3,
|
| 1225 |
+
"fps": 20.0
|
| 1226 |
+
}
|
| 1227 |
+
},
|
| 1228 |
+
"state": {
|
| 1229 |
+
"eef_position": {
|
| 1230 |
+
"absolute": true,
|
| 1231 |
+
"rotation_type": null,
|
| 1232 |
+
"shape": [
|
| 1233 |
+
3
|
| 1234 |
+
],
|
| 1235 |
+
"continuous": true
|
| 1236 |
+
},
|
| 1237 |
+
"eef_rotation": {
|
| 1238 |
+
"absolute": true,
|
| 1239 |
+
"rotation_type": "axis_angle",
|
| 1240 |
+
"shape": [
|
| 1241 |
+
3
|
| 1242 |
+
],
|
| 1243 |
+
"continuous": true
|
| 1244 |
+
},
|
| 1245 |
+
"libero_gripper_position": {
|
| 1246 |
+
"absolute": true,
|
| 1247 |
+
"rotation_type": null,
|
| 1248 |
+
"shape": [
|
| 1249 |
+
2
|
| 1250 |
+
],
|
| 1251 |
+
"continuous": true
|
| 1252 |
+
}
|
| 1253 |
+
},
|
| 1254 |
+
"action": {
|
| 1255 |
+
"eef_position": {
|
| 1256 |
+
"absolute": false,
|
| 1257 |
+
"rotation_type": null,
|
| 1258 |
+
"shape": [
|
| 1259 |
+
3
|
| 1260 |
+
],
|
| 1261 |
+
"continuous": true
|
| 1262 |
+
},
|
| 1263 |
+
"eef_rotation": {
|
| 1264 |
+
"absolute": false,
|
| 1265 |
+
"rotation_type": "axis_angle",
|
| 1266 |
+
"shape": [
|
| 1267 |
+
3
|
| 1268 |
+
],
|
| 1269 |
+
"continuous": true
|
| 1270 |
+
},
|
| 1271 |
+
"gripper_position": {
|
| 1272 |
+
"absolute": true,
|
| 1273 |
+
"rotation_type": null,
|
| 1274 |
+
"shape": [
|
| 1275 |
+
1
|
| 1276 |
+
],
|
| 1277 |
+
"continuous": true
|
| 1278 |
+
}
|
| 1279 |
+
}
|
| 1280 |
+
},
|
| 1281 |
+
"embodiment_tag": "new_embodiment",
|
| 1282 |
+
"stats_level": "task"
|
| 1283 |
+
}
|
| 1284 |
+
}
|
| 1285 |
+
}
|
libero-plus/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
libero-plus/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73af03fb8b42b2be12b95f3e440f67609759584107802584b325176df5c7c2d9
|
| 3 |
+
size 11201369880
|
libero-plus/special_tokens_map.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>",
|
| 16 |
+
"<img>",
|
| 17 |
+
"</img>",
|
| 18 |
+
"<IMG_CONTEXT>",
|
| 19 |
+
"<quad>",
|
| 20 |
+
"</quad>",
|
| 21 |
+
"<ref>",
|
| 22 |
+
"</ref>",
|
| 23 |
+
"<box>",
|
| 24 |
+
"</box>"
|
| 25 |
+
],
|
| 26 |
+
"eos_token": {
|
| 27 |
+
"content": "<|im_end|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"pad_token": {
|
| 34 |
+
"content": "<|endoftext|>",
|
| 35 |
+
"lstrip": false,
|
| 36 |
+
"normalized": false,
|
| 37 |
+
"rstrip": false,
|
| 38 |
+
"single_word": false
|
| 39 |
+
}
|
| 40 |
+
}
|
libero-plus/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12806c7c382822e3b8215170269ab902ff55298f14b3578a02436dde5f7c1d84
|
| 3 |
+
size 11427559
|
libero-plus/tokenizer_config.json
ADDED
|
@@ -0,0 +1,458 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"151643": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"151644": {
|
| 15 |
+
"content": "<|im_start|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"151645": {
|
| 23 |
+
"content": "<|im_end|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"151646": {
|
| 31 |
+
"content": "<|object_ref_start|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"151647": {
|
| 39 |
+
"content": "<|object_ref_end|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"151648": {
|
| 47 |
+
"content": "<|box_start|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"151649": {
|
| 55 |
+
"content": "<|box_end|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"151650": {
|
| 63 |
+
"content": "<|quad_start|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"151651": {
|
| 71 |
+
"content": "<|quad_end|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"151652": {
|
| 79 |
+
"content": "<|vision_start|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"151653": {
|
| 87 |
+
"content": "<|vision_end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"151654": {
|
| 95 |
+
"content": "<|vision_pad|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"151655": {
|
| 103 |
+
"content": "<|image_pad|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"151656": {
|
| 111 |
+
"content": "<|video_pad|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"151657": {
|
| 119 |
+
"content": "<tool_call>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"151658": {
|
| 127 |
+
"content": "</tool_call>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"151659": {
|
| 135 |
+
"content": "<|fim_prefix|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"151660": {
|
| 143 |
+
"content": "<|fim_middle|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"151661": {
|
| 151 |
+
"content": "<|fim_suffix|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"151662": {
|
| 159 |
+
"content": "<|fim_pad|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"151663": {
|
| 167 |
+
"content": "<|repo_name|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"151664": {
|
| 175 |
+
"content": "<|file_sep|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
},
|
| 182 |
+
"151665": {
|
| 183 |
+
"content": "<tool_response>",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": false,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": false
|
| 189 |
+
},
|
| 190 |
+
"151666": {
|
| 191 |
+
"content": "</tool_response>",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": false,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": false
|
| 197 |
+
},
|
| 198 |
+
"151667": {
|
| 199 |
+
"content": "<think>",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": false
|
| 205 |
+
},
|
| 206 |
+
"151668": {
|
| 207 |
+
"content": "</think>",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": false,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false,
|
| 212 |
+
"special": false
|
| 213 |
+
},
|
| 214 |
+
"151669": {
|
| 215 |
+
"content": "<img>",
|
| 216 |
+
"lstrip": false,
|
| 217 |
+
"normalized": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"single_word": false,
|
| 220 |
+
"special": true
|
| 221 |
+
},
|
| 222 |
+
"151670": {
|
| 223 |
+
"content": "</img>",
|
| 224 |
+
"lstrip": false,
|
| 225 |
+
"normalized": false,
|
| 226 |
+
"rstrip": false,
|
| 227 |
+
"single_word": false,
|
| 228 |
+
"special": true
|
| 229 |
+
},
|
| 230 |
+
"151671": {
|
| 231 |
+
"content": "<IMG_CONTEXT>",
|
| 232 |
+
"lstrip": false,
|
| 233 |
+
"normalized": false,
|
| 234 |
+
"rstrip": false,
|
| 235 |
+
"single_word": false,
|
| 236 |
+
"special": true
|
| 237 |
+
},
|
| 238 |
+
"151672": {
|
| 239 |
+
"content": "<quad>",
|
| 240 |
+
"lstrip": false,
|
| 241 |
+
"normalized": false,
|
| 242 |
+
"rstrip": false,
|
| 243 |
+
"single_word": false,
|
| 244 |
+
"special": true
|
| 245 |
+
},
|
| 246 |
+
"151673": {
|
| 247 |
+
"content": "</quad>",
|
| 248 |
+
"lstrip": false,
|
| 249 |
+
"normalized": false,
|
| 250 |
+
"rstrip": false,
|
| 251 |
+
"single_word": false,
|
| 252 |
+
"special": true
|
| 253 |
+
},
|
| 254 |
+
"151674": {
|
| 255 |
+
"content": "<ref>",
|
| 256 |
+
"lstrip": false,
|
| 257 |
+
"normalized": false,
|
| 258 |
+
"rstrip": false,
|
| 259 |
+
"single_word": false,
|
| 260 |
+
"special": true
|
| 261 |
+
},
|
| 262 |
+
"151675": {
|
| 263 |
+
"content": "</ref>",
|
| 264 |
+
"lstrip": false,
|
| 265 |
+
"normalized": false,
|
| 266 |
+
"rstrip": false,
|
| 267 |
+
"single_word": false,
|
| 268 |
+
"special": true
|
| 269 |
+
},
|
| 270 |
+
"151676": {
|
| 271 |
+
"content": "<box>",
|
| 272 |
+
"lstrip": false,
|
| 273 |
+
"normalized": false,
|
| 274 |
+
"rstrip": false,
|
| 275 |
+
"single_word": false,
|
| 276 |
+
"special": true
|
| 277 |
+
},
|
| 278 |
+
"151677": {
|
| 279 |
+
"content": "</box>",
|
| 280 |
+
"lstrip": false,
|
| 281 |
+
"normalized": false,
|
| 282 |
+
"rstrip": false,
|
| 283 |
+
"single_word": false,
|
| 284 |
+
"special": true
|
| 285 |
+
},
|
| 286 |
+
"151678": {
|
| 287 |
+
"content": "<vision_start>",
|
| 288 |
+
"lstrip": false,
|
| 289 |
+
"normalized": false,
|
| 290 |
+
"rstrip": false,
|
| 291 |
+
"single_word": false,
|
| 292 |
+
"special": true
|
| 293 |
+
},
|
| 294 |
+
"151679": {
|
| 295 |
+
"content": "<vision_end>",
|
| 296 |
+
"lstrip": false,
|
| 297 |
+
"normalized": false,
|
| 298 |
+
"rstrip": false,
|
| 299 |
+
"single_word": false,
|
| 300 |
+
"special": true
|
| 301 |
+
},
|
| 302 |
+
"151680": {
|
| 303 |
+
"content": "<|tac_start|>",
|
| 304 |
+
"lstrip": false,
|
| 305 |
+
"normalized": false,
|
| 306 |
+
"rstrip": false,
|
| 307 |
+
"single_word": false,
|
| 308 |
+
"special": true
|
| 309 |
+
},
|
| 310 |
+
"151681": {
|
| 311 |
+
"content": "<|tac_end|>",
|
| 312 |
+
"lstrip": false,
|
| 313 |
+
"normalized": false,
|
| 314 |
+
"rstrip": false,
|
| 315 |
+
"single_word": false,
|
| 316 |
+
"special": true
|
| 317 |
+
},
|
| 318 |
+
"151682": {
|
| 319 |
+
"content": "<|action_start|>",
|
| 320 |
+
"lstrip": false,
|
| 321 |
+
"normalized": false,
|
| 322 |
+
"rstrip": false,
|
| 323 |
+
"single_word": false,
|
| 324 |
+
"special": true
|
| 325 |
+
},
|
| 326 |
+
"151683": {
|
| 327 |
+
"content": "<|action_end|>",
|
| 328 |
+
"lstrip": false,
|
| 329 |
+
"normalized": false,
|
| 330 |
+
"rstrip": false,
|
| 331 |
+
"single_word": false,
|
| 332 |
+
"special": true
|
| 333 |
+
},
|
| 334 |
+
"151684": {
|
| 335 |
+
"content": "<|state_start|>",
|
| 336 |
+
"lstrip": false,
|
| 337 |
+
"normalized": false,
|
| 338 |
+
"rstrip": false,
|
| 339 |
+
"single_word": false,
|
| 340 |
+
"special": true
|
| 341 |
+
},
|
| 342 |
+
"151685": {
|
| 343 |
+
"content": "<|state_end|>",
|
| 344 |
+
"lstrip": false,
|
| 345 |
+
"normalized": false,
|
| 346 |
+
"rstrip": false,
|
| 347 |
+
"single_word": false,
|
| 348 |
+
"special": true
|
| 349 |
+
},
|
| 350 |
+
"151686": {
|
| 351 |
+
"content": "<PROP_CONTEXT>",
|
| 352 |
+
"lstrip": false,
|
| 353 |
+
"normalized": false,
|
| 354 |
+
"rstrip": false,
|
| 355 |
+
"single_word": false,
|
| 356 |
+
"special": true
|
| 357 |
+
},
|
| 358 |
+
"151687": {
|
| 359 |
+
"content": "<ACTION_TOKEN_0>",
|
| 360 |
+
"lstrip": false,
|
| 361 |
+
"normalized": false,
|
| 362 |
+
"rstrip": false,
|
| 363 |
+
"single_word": false,
|
| 364 |
+
"special": true
|
| 365 |
+
},
|
| 366 |
+
"151688": {
|
| 367 |
+
"content": "<ACTION_TOKEN_1>",
|
| 368 |
+
"lstrip": false,
|
| 369 |
+
"normalized": false,
|
| 370 |
+
"rstrip": false,
|
| 371 |
+
"single_word": false,
|
| 372 |
+
"special": true
|
| 373 |
+
},
|
| 374 |
+
"151689": {
|
| 375 |
+
"content": "<ACTION_TOKEN_2>",
|
| 376 |
+
"lstrip": false,
|
| 377 |
+
"normalized": false,
|
| 378 |
+
"rstrip": false,
|
| 379 |
+
"single_word": false,
|
| 380 |
+
"special": true
|
| 381 |
+
},
|
| 382 |
+
"151690": {
|
| 383 |
+
"content": "<ACTION_TOKEN_3>",
|
| 384 |
+
"lstrip": false,
|
| 385 |
+
"normalized": false,
|
| 386 |
+
"rstrip": false,
|
| 387 |
+
"single_word": false,
|
| 388 |
+
"special": true
|
| 389 |
+
},
|
| 390 |
+
"151691": {
|
| 391 |
+
"content": "<ACTION_TOKEN_4>",
|
| 392 |
+
"lstrip": false,
|
| 393 |
+
"normalized": false,
|
| 394 |
+
"rstrip": false,
|
| 395 |
+
"single_word": false,
|
| 396 |
+
"special": true
|
| 397 |
+
},
|
| 398 |
+
"151692": {
|
| 399 |
+
"content": "<ACTION_TOKEN_5>",
|
| 400 |
+
"lstrip": false,
|
| 401 |
+
"normalized": false,
|
| 402 |
+
"rstrip": false,
|
| 403 |
+
"single_word": false,
|
| 404 |
+
"special": true
|
| 405 |
+
},
|
| 406 |
+
"151693": {
|
| 407 |
+
"content": "<ACTION_TOKEN_6>",
|
| 408 |
+
"lstrip": false,
|
| 409 |
+
"normalized": false,
|
| 410 |
+
"rstrip": false,
|
| 411 |
+
"single_word": false,
|
| 412 |
+
"special": true
|
| 413 |
+
},
|
| 414 |
+
"151694": {
|
| 415 |
+
"content": "<ACTION_TOKEN_7>",
|
| 416 |
+
"lstrip": false,
|
| 417 |
+
"normalized": false,
|
| 418 |
+
"rstrip": false,
|
| 419 |
+
"single_word": false,
|
| 420 |
+
"special": true
|
| 421 |
+
}
|
| 422 |
+
},
|
| 423 |
+
"additional_special_tokens": [
|
| 424 |
+
"<|im_start|>",
|
| 425 |
+
"<|im_end|>",
|
| 426 |
+
"<|object_ref_start|>",
|
| 427 |
+
"<|object_ref_end|>",
|
| 428 |
+
"<|box_start|>",
|
| 429 |
+
"<|box_end|>",
|
| 430 |
+
"<|quad_start|>",
|
| 431 |
+
"<|quad_end|>",
|
| 432 |
+
"<|vision_start|>",
|
| 433 |
+
"<|vision_end|>",
|
| 434 |
+
"<|vision_pad|>",
|
| 435 |
+
"<|image_pad|>",
|
| 436 |
+
"<|video_pad|>",
|
| 437 |
+
"<img>",
|
| 438 |
+
"</img>",
|
| 439 |
+
"<IMG_CONTEXT>",
|
| 440 |
+
"<quad>",
|
| 441 |
+
"</quad>",
|
| 442 |
+
"<ref>",
|
| 443 |
+
"</ref>",
|
| 444 |
+
"<box>",
|
| 445 |
+
"</box>"
|
| 446 |
+
],
|
| 447 |
+
"bos_token": null,
|
| 448 |
+
"clean_up_tokenization_spaces": false,
|
| 449 |
+
"eos_token": "<|im_end|>",
|
| 450 |
+
"errors": "replace",
|
| 451 |
+
"extra_special_tokens": {},
|
| 452 |
+
"model_max_length": 14588,
|
| 453 |
+
"pad_token": "<|endoftext|>",
|
| 454 |
+
"processor_class": "InternVLProcessor",
|
| 455 |
+
"split_special_tokens": false,
|
| 456 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 457 |
+
"unk_token": null
|
| 458 |
+
}
|
libero-plus/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
libero/added_tokens.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</box>": 151677,
|
| 3 |
+
"</img>": 151670,
|
| 4 |
+
"</quad>": 151673,
|
| 5 |
+
"</ref>": 151675,
|
| 6 |
+
"</think>": 151668,
|
| 7 |
+
"</tool_call>": 151658,
|
| 8 |
+
"</tool_response>": 151666,
|
| 9 |
+
"<ACTION_TOKEN_0>": 151687,
|
| 10 |
+
"<ACTION_TOKEN_1>": 151688,
|
| 11 |
+
"<ACTION_TOKEN_2>": 151689,
|
| 12 |
+
"<ACTION_TOKEN_3>": 151690,
|
| 13 |
+
"<ACTION_TOKEN_4>": 151691,
|
| 14 |
+
"<ACTION_TOKEN_5>": 151692,
|
| 15 |
+
"<ACTION_TOKEN_6>": 151693,
|
| 16 |
+
"<ACTION_TOKEN_7>": 151694,
|
| 17 |
+
"<IMG_CONTEXT>": 151671,
|
| 18 |
+
"<PROP_CONTEXT>": 151686,
|
| 19 |
+
"<box>": 151676,
|
| 20 |
+
"<img>": 151669,
|
| 21 |
+
"<quad>": 151672,
|
| 22 |
+
"<ref>": 151674,
|
| 23 |
+
"<think>": 151667,
|
| 24 |
+
"<tool_call>": 151657,
|
| 25 |
+
"<tool_response>": 151665,
|
| 26 |
+
"<vision_end>": 151679,
|
| 27 |
+
"<vision_start>": 151678,
|
| 28 |
+
"<|action_end|>": 151683,
|
| 29 |
+
"<|action_start|>": 151682,
|
| 30 |
+
"<|box_end|>": 151649,
|
| 31 |
+
"<|box_start|>": 151648,
|
| 32 |
+
"<|endoftext|>": 151643,
|
| 33 |
+
"<|file_sep|>": 151664,
|
| 34 |
+
"<|fim_middle|>": 151660,
|
| 35 |
+
"<|fim_pad|>": 151662,
|
| 36 |
+
"<|fim_prefix|>": 151659,
|
| 37 |
+
"<|fim_suffix|>": 151661,
|
| 38 |
+
"<|im_end|>": 151645,
|
| 39 |
+
"<|im_start|>": 151644,
|
| 40 |
+
"<|image_pad|>": 151655,
|
| 41 |
+
"<|object_ref_end|>": 151647,
|
| 42 |
+
"<|object_ref_start|>": 151646,
|
| 43 |
+
"<|quad_end|>": 151651,
|
| 44 |
+
"<|quad_start|>": 151650,
|
| 45 |
+
"<|repo_name|>": 151663,
|
| 46 |
+
"<|state_end|>": 151685,
|
| 47 |
+
"<|state_start|>": 151684,
|
| 48 |
+
"<|tac_end|>": 151681,
|
| 49 |
+
"<|tac_start|>": 151680,
|
| 50 |
+
"<|video_pad|>": 151656,
|
| 51 |
+
"<|vision_end|>": 151653,
|
| 52 |
+
"<|vision_pad|>": 151654,
|
| 53 |
+
"<|vision_start|>": 151652
|
| 54 |
+
}
|
libero/chat_template.jinja
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{{'<|im_start|>' + message['role'] + '
|
| 2 |
+
'}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<image>
|
| 3 |
+
' }}{% elif content['type'] == 'video' %}{{ '<video>
|
| 4 |
+
' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>
|
| 5 |
+
'}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
|
| 6 |
+
' }}{% endif %}
|
libero/config.json
ADDED
|
@@ -0,0 +1,366 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"return_dict": true,
|
| 3 |
+
"output_hidden_states": false,
|
| 4 |
+
"torchscript": false,
|
| 5 |
+
"dtype": null,
|
| 6 |
+
"pruned_heads": {},
|
| 7 |
+
"tie_word_embeddings": true,
|
| 8 |
+
"chunk_size_feed_forward": 0,
|
| 9 |
+
"is_encoder_decoder": false,
|
| 10 |
+
"is_decoder": false,
|
| 11 |
+
"cross_attention_hidden_size": null,
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"tie_encoder_decoder": false,
|
| 14 |
+
"architectures": null,
|
| 15 |
+
"finetuning_task": null,
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "LABEL_0",
|
| 18 |
+
"1": "LABEL_1"
|
| 19 |
+
},
|
| 20 |
+
"label2id": {
|
| 21 |
+
"LABEL_0": 0,
|
| 22 |
+
"LABEL_1": 1
|
| 23 |
+
},
|
| 24 |
+
"task_specific_params": null,
|
| 25 |
+
"problem_type": null,
|
| 26 |
+
"tokenizer_class": null,
|
| 27 |
+
"prefix": null,
|
| 28 |
+
"bos_token_id": null,
|
| 29 |
+
"pad_token_id": null,
|
| 30 |
+
"eos_token_id": null,
|
| 31 |
+
"sep_token_id": null,
|
| 32 |
+
"decoder_start_token_id": null,
|
| 33 |
+
"max_length": 20,
|
| 34 |
+
"min_length": 0,
|
| 35 |
+
"do_sample": false,
|
| 36 |
+
"early_stopping": false,
|
| 37 |
+
"num_beams": 1,
|
| 38 |
+
"temperature": 1.0,
|
| 39 |
+
"top_k": 50,
|
| 40 |
+
"top_p": 1.0,
|
| 41 |
+
"typical_p": 1.0,
|
| 42 |
+
"repetition_penalty": 1.0,
|
| 43 |
+
"length_penalty": 1.0,
|
| 44 |
+
"no_repeat_ngram_size": 0,
|
| 45 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 46 |
+
"bad_words_ids": null,
|
| 47 |
+
"num_return_sequences": 1,
|
| 48 |
+
"output_scores": false,
|
| 49 |
+
"return_dict_in_generate": false,
|
| 50 |
+
"forced_bos_token_id": null,
|
| 51 |
+
"forced_eos_token_id": null,
|
| 52 |
+
"remove_invalid_values": false,
|
| 53 |
+
"exponential_decay_length_penalty": null,
|
| 54 |
+
"suppress_tokens": null,
|
| 55 |
+
"begin_suppress_tokens": null,
|
| 56 |
+
"num_beam_groups": 1,
|
| 57 |
+
"diversity_penalty": 0.0,
|
| 58 |
+
"_name_or_path": "",
|
| 59 |
+
"transformers_version": "4.57.1",
|
| 60 |
+
"use_mpg": false,
|
| 61 |
+
"mpg_num_projections": 32,
|
| 62 |
+
"mpg_lambda": 0.1,
|
| 63 |
+
"mpg_use_stop_gradient": true,
|
| 64 |
+
"mpg_refinement_iters": 1,
|
| 65 |
+
"mpg_gate_temperature": 1.0,
|
| 66 |
+
"use_training_time_rtc": false,
|
| 67 |
+
"simulated_delay": 0,
|
| 68 |
+
"rtc_delay_exp_weight": true,
|
| 69 |
+
"use_inference_prefix_overwrite": true,
|
| 70 |
+
"tf_legacy_loss": false,
|
| 71 |
+
"use_bfloat16": false,
|
| 72 |
+
"llm_config": {
|
| 73 |
+
"vocab_size": 151695,
|
| 74 |
+
"max_position_embeddings": 40960,
|
| 75 |
+
"hidden_size": 2048,
|
| 76 |
+
"intermediate_size": 6144,
|
| 77 |
+
"num_hidden_layers": 28,
|
| 78 |
+
"num_attention_heads": 16,
|
| 79 |
+
"use_sliding_window": false,
|
| 80 |
+
"sliding_window": null,
|
| 81 |
+
"max_window_layers": 28,
|
| 82 |
+
"num_key_value_heads": 8,
|
| 83 |
+
"hidden_act": "silu",
|
| 84 |
+
"initializer_range": 0.02,
|
| 85 |
+
"rms_norm_eps": 1e-06,
|
| 86 |
+
"use_cache": false,
|
| 87 |
+
"rope_theta": 1000000,
|
| 88 |
+
"rope_scaling": null,
|
| 89 |
+
"attention_bias": false,
|
| 90 |
+
"attention_dropout": 0.0,
|
| 91 |
+
"is_causal": true,
|
| 92 |
+
"return_dict": true,
|
| 93 |
+
"output_hidden_states": false,
|
| 94 |
+
"torchscript": false,
|
| 95 |
+
"dtype": "bfloat16",
|
| 96 |
+
"pruned_heads": {},
|
| 97 |
+
"tie_word_embeddings": false,
|
| 98 |
+
"chunk_size_feed_forward": 0,
|
| 99 |
+
"is_encoder_decoder": false,
|
| 100 |
+
"is_decoder": false,
|
| 101 |
+
"cross_attention_hidden_size": null,
|
| 102 |
+
"add_cross_attention": false,
|
| 103 |
+
"tie_encoder_decoder": false,
|
| 104 |
+
"architectures": [
|
| 105 |
+
"Qwen3ForCausalLM"
|
| 106 |
+
],
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"id2label": {
|
| 109 |
+
"0": "LABEL_0",
|
| 110 |
+
"1": "LABEL_1"
|
| 111 |
+
},
|
| 112 |
+
"label2id": {
|
| 113 |
+
"LABEL_0": 0,
|
| 114 |
+
"LABEL_1": 1
|
| 115 |
+
},
|
| 116 |
+
"task_specific_params": null,
|
| 117 |
+
"problem_type": null,
|
| 118 |
+
"tokenizer_class": null,
|
| 119 |
+
"prefix": null,
|
| 120 |
+
"bos_token_id": 151643,
|
| 121 |
+
"pad_token_id": null,
|
| 122 |
+
"eos_token_id": 151645,
|
| 123 |
+
"sep_token_id": null,
|
| 124 |
+
"decoder_start_token_id": null,
|
| 125 |
+
"max_length": 20,
|
| 126 |
+
"min_length": 0,
|
| 127 |
+
"do_sample": false,
|
| 128 |
+
"early_stopping": false,
|
| 129 |
+
"num_beams": 1,
|
| 130 |
+
"temperature": 1.0,
|
| 131 |
+
"top_k": 50,
|
| 132 |
+
"top_p": 1.0,
|
| 133 |
+
"typical_p": 1.0,
|
| 134 |
+
"repetition_penalty": 1.0,
|
| 135 |
+
"length_penalty": 1.0,
|
| 136 |
+
"no_repeat_ngram_size": 0,
|
| 137 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 138 |
+
"bad_words_ids": null,
|
| 139 |
+
"num_return_sequences": 1,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"return_dict_in_generate": false,
|
| 142 |
+
"forced_bos_token_id": null,
|
| 143 |
+
"forced_eos_token_id": null,
|
| 144 |
+
"remove_invalid_values": false,
|
| 145 |
+
"exponential_decay_length_penalty": null,
|
| 146 |
+
"suppress_tokens": null,
|
| 147 |
+
"begin_suppress_tokens": null,
|
| 148 |
+
"num_beam_groups": 1,
|
| 149 |
+
"diversity_penalty": 0.0,
|
| 150 |
+
"_name_or_path": "/root/codespace/checkpoints/Qwen3-1.7B",
|
| 151 |
+
"debug": false,
|
| 152 |
+
"ep_size": 1,
|
| 153 |
+
"head_dim": 128,
|
| 154 |
+
"micro_forward": false,
|
| 155 |
+
"model_type": "qwen3",
|
| 156 |
+
"skip_checkpoint": false,
|
| 157 |
+
"use_deepep": false,
|
| 158 |
+
"tf_legacy_loss": false,
|
| 159 |
+
"use_bfloat16": false,
|
| 160 |
+
"qk_norm": true,
|
| 161 |
+
"layer_module": "Qwen3MoTDecoderLayer",
|
| 162 |
+
"use_mot": true,
|
| 163 |
+
"expert_config": {
|
| 164 |
+
"vocab_size": 151936,
|
| 165 |
+
"max_position_embeddings": 40960,
|
| 166 |
+
"hidden_size": 1024,
|
| 167 |
+
"intermediate_size": 3072,
|
| 168 |
+
"num_hidden_layers": 28,
|
| 169 |
+
"num_attention_heads": 16,
|
| 170 |
+
"use_sliding_window": false,
|
| 171 |
+
"sliding_window": null,
|
| 172 |
+
"max_window_layers": 28,
|
| 173 |
+
"num_key_value_heads": 8,
|
| 174 |
+
"hidden_act": "silu",
|
| 175 |
+
"initializer_range": 0.02,
|
| 176 |
+
"rms_norm_eps": 1e-06,
|
| 177 |
+
"use_cache": true,
|
| 178 |
+
"rope_theta": 1000000,
|
| 179 |
+
"rope_scaling": null,
|
| 180 |
+
"attention_bias": false,
|
| 181 |
+
"attention_dropout": 0.0,
|
| 182 |
+
"is_causal": true,
|
| 183 |
+
"return_dict": true,
|
| 184 |
+
"output_hidden_states": false,
|
| 185 |
+
"torchscript": false,
|
| 186 |
+
"dtype": "bfloat16",
|
| 187 |
+
"pruned_heads": {},
|
| 188 |
+
"tie_word_embeddings": true,
|
| 189 |
+
"chunk_size_feed_forward": 0,
|
| 190 |
+
"is_encoder_decoder": false,
|
| 191 |
+
"is_decoder": false,
|
| 192 |
+
"cross_attention_hidden_size": null,
|
| 193 |
+
"add_cross_attention": false,
|
| 194 |
+
"tie_encoder_decoder": false,
|
| 195 |
+
"architectures": [
|
| 196 |
+
"Qwen3ForCausalLM"
|
| 197 |
+
],
|
| 198 |
+
"finetuning_task": null,
|
| 199 |
+
"id2label": {
|
| 200 |
+
"0": "LABEL_0",
|
| 201 |
+
"1": "LABEL_1"
|
| 202 |
+
},
|
| 203 |
+
"label2id": {
|
| 204 |
+
"LABEL_0": 0,
|
| 205 |
+
"LABEL_1": 1
|
| 206 |
+
},
|
| 207 |
+
"task_specific_params": null,
|
| 208 |
+
"problem_type": null,
|
| 209 |
+
"tokenizer_class": null,
|
| 210 |
+
"prefix": null,
|
| 211 |
+
"bos_token_id": 151643,
|
| 212 |
+
"pad_token_id": null,
|
| 213 |
+
"eos_token_id": 151645,
|
| 214 |
+
"sep_token_id": null,
|
| 215 |
+
"decoder_start_token_id": null,
|
| 216 |
+
"max_length": 20,
|
| 217 |
+
"min_length": 0,
|
| 218 |
+
"do_sample": false,
|
| 219 |
+
"early_stopping": false,
|
| 220 |
+
"num_beams": 1,
|
| 221 |
+
"temperature": 1.0,
|
| 222 |
+
"top_k": 50,
|
| 223 |
+
"top_p": 1.0,
|
| 224 |
+
"typical_p": 1.0,
|
| 225 |
+
"repetition_penalty": 1.0,
|
| 226 |
+
"length_penalty": 1.0,
|
| 227 |
+
"no_repeat_ngram_size": 0,
|
| 228 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 229 |
+
"bad_words_ids": null,
|
| 230 |
+
"num_return_sequences": 1,
|
| 231 |
+
"output_scores": false,
|
| 232 |
+
"return_dict_in_generate": false,
|
| 233 |
+
"forced_bos_token_id": null,
|
| 234 |
+
"forced_eos_token_id": null,
|
| 235 |
+
"remove_invalid_values": false,
|
| 236 |
+
"exponential_decay_length_penalty": null,
|
| 237 |
+
"suppress_tokens": null,
|
| 238 |
+
"begin_suppress_tokens": null,
|
| 239 |
+
"num_beam_groups": 1,
|
| 240 |
+
"diversity_penalty": 0.0,
|
| 241 |
+
"_name_or_path": "",
|
| 242 |
+
"head_dim": 128,
|
| 243 |
+
"model_type": "qwen3",
|
| 244 |
+
"tf_legacy_loss": false,
|
| 245 |
+
"use_bfloat16": false,
|
| 246 |
+
"qk_norm": true,
|
| 247 |
+
"layer_module": "Qwen3DecoderLayer",
|
| 248 |
+
"output_attentions": false
|
| 249 |
+
},
|
| 250 |
+
"attn_implementation": "flash_attention_2",
|
| 251 |
+
"output_attentions": false
|
| 252 |
+
},
|
| 253 |
+
"vit_config": {
|
| 254 |
+
"return_dict": true,
|
| 255 |
+
"output_hidden_states": false,
|
| 256 |
+
"torchscript": false,
|
| 257 |
+
"dtype": "bfloat16",
|
| 258 |
+
"pruned_heads": {},
|
| 259 |
+
"tie_word_embeddings": true,
|
| 260 |
+
"chunk_size_feed_forward": 0,
|
| 261 |
+
"is_encoder_decoder": false,
|
| 262 |
+
"is_decoder": false,
|
| 263 |
+
"cross_attention_hidden_size": null,
|
| 264 |
+
"add_cross_attention": false,
|
| 265 |
+
"tie_encoder_decoder": false,
|
| 266 |
+
"architectures": [
|
| 267 |
+
"InternVisionModel"
|
| 268 |
+
],
|
| 269 |
+
"finetuning_task": null,
|
| 270 |
+
"id2label": {
|
| 271 |
+
"0": "LABEL_0",
|
| 272 |
+
"1": "LABEL_1"
|
| 273 |
+
},
|
| 274 |
+
"label2id": {
|
| 275 |
+
"LABEL_0": 0,
|
| 276 |
+
"LABEL_1": 1
|
| 277 |
+
},
|
| 278 |
+
"task_specific_params": null,
|
| 279 |
+
"problem_type": null,
|
| 280 |
+
"tokenizer_class": null,
|
| 281 |
+
"prefix": null,
|
| 282 |
+
"bos_token_id": null,
|
| 283 |
+
"pad_token_id": null,
|
| 284 |
+
"eos_token_id": null,
|
| 285 |
+
"sep_token_id": null,
|
| 286 |
+
"decoder_start_token_id": null,
|
| 287 |
+
"max_length": 20,
|
| 288 |
+
"min_length": 0,
|
| 289 |
+
"do_sample": false,
|
| 290 |
+
"early_stopping": false,
|
| 291 |
+
"num_beams": 1,
|
| 292 |
+
"temperature": 1.0,
|
| 293 |
+
"top_k": 50,
|
| 294 |
+
"top_p": 1.0,
|
| 295 |
+
"typical_p": 1.0,
|
| 296 |
+
"repetition_penalty": 1.0,
|
| 297 |
+
"length_penalty": 1.0,
|
| 298 |
+
"no_repeat_ngram_size": 0,
|
| 299 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 300 |
+
"bad_words_ids": null,
|
| 301 |
+
"num_return_sequences": 1,
|
| 302 |
+
"output_scores": false,
|
| 303 |
+
"return_dict_in_generate": false,
|
| 304 |
+
"forced_bos_token_id": null,
|
| 305 |
+
"forced_eos_token_id": null,
|
| 306 |
+
"remove_invalid_values": false,
|
| 307 |
+
"exponential_decay_length_penalty": null,
|
| 308 |
+
"suppress_tokens": null,
|
| 309 |
+
"begin_suppress_tokens": null,
|
| 310 |
+
"num_beam_groups": 1,
|
| 311 |
+
"diversity_penalty": 0.0,
|
| 312 |
+
"_name_or_path": "",
|
| 313 |
+
"auto_map": {
|
| 314 |
+
"AutoConfig": "configuration_intern_vit.InternVisionConfig",
|
| 315 |
+
"AutoModel": "modeling_intern_vit.InternVisionModel"
|
| 316 |
+
},
|
| 317 |
+
"model_type": "intern_vit_6b",
|
| 318 |
+
"use_fa3": false,
|
| 319 |
+
"tf_legacy_loss": false,
|
| 320 |
+
"use_bfloat16": false,
|
| 321 |
+
"hidden_size": 1024,
|
| 322 |
+
"intermediate_size": 4096,
|
| 323 |
+
"dropout": 0.0,
|
| 324 |
+
"drop_path_rate": 0.0,
|
| 325 |
+
"num_hidden_layers": 24,
|
| 326 |
+
"num_attention_heads": 16,
|
| 327 |
+
"num_channels": 3,
|
| 328 |
+
"patch_size": 14,
|
| 329 |
+
"image_size": 224,
|
| 330 |
+
"initializer_range": 0.02,
|
| 331 |
+
"initializer_factor": 1.0,
|
| 332 |
+
"attention_dropout": 0.0,
|
| 333 |
+
"layer_norm_eps": 1e-06,
|
| 334 |
+
"hidden_act": "gelu",
|
| 335 |
+
"norm_type": "layer_norm",
|
| 336 |
+
"qkv_bias": true,
|
| 337 |
+
"qk_normalization": false,
|
| 338 |
+
"use_flash_attn": true,
|
| 339 |
+
"select_layer": -1,
|
| 340 |
+
"downsample_ratio": 0.5,
|
| 341 |
+
"output_attentions": false
|
| 342 |
+
},
|
| 343 |
+
"connector_arch": "internvl_connector",
|
| 344 |
+
"template": "being_h0",
|
| 345 |
+
"select_layer": -1,
|
| 346 |
+
"force_image_size": 224,
|
| 347 |
+
"downsample_ratio": 0.5,
|
| 348 |
+
"action_chunk_length": 8,
|
| 349 |
+
"loss_func": "l1",
|
| 350 |
+
"gen_action_type": "prop_hidden",
|
| 351 |
+
"layer_select_for_action": -1,
|
| 352 |
+
"action_token_num": 8,
|
| 353 |
+
"learnable_action_query": false,
|
| 354 |
+
"prompt_template": "long",
|
| 355 |
+
"use_expert": true,
|
| 356 |
+
"use_flow_matching": true,
|
| 357 |
+
"attn_mode": "causal",
|
| 358 |
+
"max_num_embodiments": 32,
|
| 359 |
+
"noise_beta_alpha": 1.5,
|
| 360 |
+
"noise_beta_beta": 1.0,
|
| 361 |
+
"num_timestep_buckets": 1000,
|
| 362 |
+
"noise_s": 0.999,
|
| 363 |
+
"num_inference_timesteps": 4,
|
| 364 |
+
"model_type": "beingh",
|
| 365 |
+
"output_attentions": false
|
| 366 |
+
}
|
libero/libero_posttrain_metadata.json
ADDED
|
@@ -0,0 +1,1285 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"libero_posttrain": {
|
| 3 |
+
"statistics": {
|
| 4 |
+
"state": {
|
| 5 |
+
"eef_rotation": {
|
| 6 |
+
"max": [
|
| 7 |
+
3.6714255809783936,
|
| 8 |
+
3.560650587081909,
|
| 9 |
+
1.386339545249939
|
| 10 |
+
],
|
| 11 |
+
"min": [
|
| 12 |
+
0.35277295112609863,
|
| 13 |
+
-3.641430377960205,
|
| 14 |
+
-1.842738389968872
|
| 15 |
+
],
|
| 16 |
+
"mean": [
|
| 17 |
+
2.9722166336668394,
|
| 18 |
+
-0.2204706193566303,
|
| 19 |
+
-0.12557939087348713
|
| 20 |
+
],
|
| 21 |
+
"std": [
|
| 22 |
+
0.34427400088135357,
|
| 23 |
+
0.9069425374402487,
|
| 24 |
+
0.3253894190906973
|
| 25 |
+
],
|
| 26 |
+
"q01": [
|
| 27 |
+
1.3085840785503386,
|
| 28 |
+
-2.886677579879761,
|
| 29 |
+
-1.1599004411697387
|
| 30 |
+
],
|
| 31 |
+
"q99": [
|
| 32 |
+
3.303542451858519,
|
| 33 |
+
2.7496529006957933,
|
| 34 |
+
0.6893712210655194
|
| 35 |
+
]
|
| 36 |
+
},
|
| 37 |
+
"eef_position": {
|
| 38 |
+
"max": [
|
| 39 |
+
0.21031762659549713,
|
| 40 |
+
0.39128610491752625,
|
| 41 |
+
1.3660105466842651
|
| 42 |
+
],
|
| 43 |
+
"min": [
|
| 44 |
+
-0.4828203022480011,
|
| 45 |
+
-0.3255046010017395,
|
| 46 |
+
0.008128180168569088
|
| 47 |
+
],
|
| 48 |
+
"mean": [
|
| 49 |
+
-0.04651873600711691,
|
| 50 |
+
0.03440890975831591,
|
| 51 |
+
0.764557162431748
|
| 52 |
+
],
|
| 53 |
+
"std": [
|
| 54 |
+
0.1049434680444918,
|
| 55 |
+
0.15176550924794815,
|
| 56 |
+
0.3785180284398934
|
| 57 |
+
],
|
| 58 |
+
"q01": [
|
| 59 |
+
-0.42401049643754957,
|
| 60 |
+
-0.2838300323486328,
|
| 61 |
+
0.009925739830359817
|
| 62 |
+
],
|
| 63 |
+
"q99": [
|
| 64 |
+
0.1530261474847791,
|
| 65 |
+
0.362916499376297,
|
| 66 |
+
1.2910678112506866
|
| 67 |
+
]
|
| 68 |
+
},
|
| 69 |
+
"libero_gripper_position": {
|
| 70 |
+
"max": [
|
| 71 |
+
0.04233968257904053,
|
| 72 |
+
0.0013633022317662835
|
| 73 |
+
],
|
| 74 |
+
"min": [
|
| 75 |
+
-0.0013586411951109767,
|
| 76 |
+
-0.042040832340717316
|
| 77 |
+
],
|
| 78 |
+
"mean": [
|
| 79 |
+
0.02691481335898233,
|
| 80 |
+
-0.02719087286926901
|
| 81 |
+
],
|
| 82 |
+
"std": [
|
| 83 |
+
0.01417594365797819,
|
| 84 |
+
0.014058877749021296
|
| 85 |
+
],
|
| 86 |
+
"q01": [
|
| 87 |
+
0.001503719249740243,
|
| 88 |
+
-0.040336399003863335
|
| 89 |
+
],
|
| 90 |
+
"q99": [
|
| 91 |
+
0.040610933862626555,
|
| 92 |
+
-0.0015016929572448147
|
| 93 |
+
]
|
| 94 |
+
}
|
| 95 |
+
},
|
| 96 |
+
"action": {
|
| 97 |
+
"eef_position": {
|
| 98 |
+
"max": [
|
| 99 |
+
0.9375,
|
| 100 |
+
0.9375,
|
| 101 |
+
0.9375
|
| 102 |
+
],
|
| 103 |
+
"min": [
|
| 104 |
+
-0.9375,
|
| 105 |
+
-0.9375,
|
| 106 |
+
-0.9375
|
| 107 |
+
],
|
| 108 |
+
"mean": [
|
| 109 |
+
0.06278154433021929,
|
| 110 |
+
0.08684070332300477,
|
| 111 |
+
-0.09037311599203464
|
| 112 |
+
],
|
| 113 |
+
"std": [
|
| 114 |
+
0.3355340671542141,
|
| 115 |
+
0.3784624131392225,
|
| 116 |
+
0.44472251877152186
|
| 117 |
+
],
|
| 118 |
+
"q01": [
|
| 119 |
+
-0.8785714507102966,
|
| 120 |
+
-0.8758928775787354,
|
| 121 |
+
-0.9375
|
| 122 |
+
],
|
| 123 |
+
"q99": [
|
| 124 |
+
0.9375,
|
| 125 |
+
0.9107142686843872,
|
| 126 |
+
0.9375
|
| 127 |
+
]
|
| 128 |
+
},
|
| 129 |
+
"eef_rotation": {
|
| 130 |
+
"max": [
|
| 131 |
+
0.3557142913341522,
|
| 132 |
+
0.375,
|
| 133 |
+
0.375
|
| 134 |
+
],
|
| 135 |
+
"min": [
|
| 136 |
+
-0.2582142949104309,
|
| 137 |
+
-0.375,
|
| 138 |
+
-0.3675000071525574
|
| 139 |
+
],
|
| 140 |
+
"mean": [
|
| 141 |
+
0.0005407439826102575,
|
| 142 |
+
0.005643430440568553,
|
| 143 |
+
-0.005229132451837535
|
| 144 |
+
],
|
| 145 |
+
"std": [
|
| 146 |
+
0.039242784623089826,
|
| 147 |
+
0.06339272159958631,
|
| 148 |
+
0.077975367145476
|
| 149 |
+
],
|
| 150 |
+
"q01": [
|
| 151 |
+
-0.1510714292526245,
|
| 152 |
+
-0.20678570866584778,
|
| 153 |
+
-0.2742857038974762
|
| 154 |
+
],
|
| 155 |
+
"q99": [
|
| 156 |
+
0.20357142388820648,
|
| 157 |
+
0.26357144117355347,
|
| 158 |
+
0.375
|
| 159 |
+
]
|
| 160 |
+
},
|
| 161 |
+
"gripper_position": {
|
| 162 |
+
"max": [
|
| 163 |
+
1.0
|
| 164 |
+
],
|
| 165 |
+
"min": [
|
| 166 |
+
0.0
|
| 167 |
+
],
|
| 168 |
+
"mean": [
|
| 169 |
+
0.5248203610828128
|
| 170 |
+
],
|
| 171 |
+
"std": [
|
| 172 |
+
0.4994850167690421
|
| 173 |
+
],
|
| 174 |
+
"q01": [
|
| 175 |
+
0.0
|
| 176 |
+
],
|
| 177 |
+
"q99": [
|
| 178 |
+
1.0
|
| 179 |
+
]
|
| 180 |
+
}
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"modalities": {
|
| 184 |
+
"video": {
|
| 185 |
+
"top_view": {
|
| 186 |
+
"resolution": [
|
| 187 |
+
256,
|
| 188 |
+
256
|
| 189 |
+
],
|
| 190 |
+
"channels": 3,
|
| 191 |
+
"fps": 20.0
|
| 192 |
+
},
|
| 193 |
+
"wrist_view": {
|
| 194 |
+
"resolution": [
|
| 195 |
+
256,
|
| 196 |
+
256
|
| 197 |
+
],
|
| 198 |
+
"channels": 3,
|
| 199 |
+
"fps": 20.0
|
| 200 |
+
}
|
| 201 |
+
},
|
| 202 |
+
"state": {
|
| 203 |
+
"eef_position": {
|
| 204 |
+
"absolute": true,
|
| 205 |
+
"rotation_type": null,
|
| 206 |
+
"shape": [
|
| 207 |
+
3
|
| 208 |
+
],
|
| 209 |
+
"continuous": true
|
| 210 |
+
},
|
| 211 |
+
"eef_rotation": {
|
| 212 |
+
"absolute": true,
|
| 213 |
+
"rotation_type": "axis_angle",
|
| 214 |
+
"shape": [
|
| 215 |
+
3
|
| 216 |
+
],
|
| 217 |
+
"continuous": true
|
| 218 |
+
},
|
| 219 |
+
"libero_gripper_position": {
|
| 220 |
+
"absolute": true,
|
| 221 |
+
"rotation_type": null,
|
| 222 |
+
"shape": [
|
| 223 |
+
2
|
| 224 |
+
],
|
| 225 |
+
"continuous": true
|
| 226 |
+
}
|
| 227 |
+
},
|
| 228 |
+
"action": {
|
| 229 |
+
"eef_position": {
|
| 230 |
+
"absolute": false,
|
| 231 |
+
"rotation_type": null,
|
| 232 |
+
"shape": [
|
| 233 |
+
3
|
| 234 |
+
],
|
| 235 |
+
"continuous": true
|
| 236 |
+
},
|
| 237 |
+
"eef_rotation": {
|
| 238 |
+
"absolute": false,
|
| 239 |
+
"rotation_type": "axis_angle",
|
| 240 |
+
"shape": [
|
| 241 |
+
3
|
| 242 |
+
],
|
| 243 |
+
"continuous": true
|
| 244 |
+
},
|
| 245 |
+
"gripper_position": {
|
| 246 |
+
"absolute": true,
|
| 247 |
+
"rotation_type": null,
|
| 248 |
+
"shape": [
|
| 249 |
+
1
|
| 250 |
+
],
|
| 251 |
+
"continuous": true
|
| 252 |
+
}
|
| 253 |
+
}
|
| 254 |
+
},
|
| 255 |
+
"embodiment_tag": "new_embodiment",
|
| 256 |
+
"default_variant": "libero_spatial_no_noops_1.0.0_lerobot",
|
| 257 |
+
"stats_level": "auto"
|
| 258 |
+
},
|
| 259 |
+
"libero_posttrain_variants": {
|
| 260 |
+
"libero_spatial_no_noops_1.0.0_lerobot": {
|
| 261 |
+
"statistics": {
|
| 262 |
+
"state": {
|
| 263 |
+
"eef_rotation": {
|
| 264 |
+
"max": [
|
| 265 |
+
3.6714255809783936,
|
| 266 |
+
3.560650587081909,
|
| 267 |
+
1.386339545249939
|
| 268 |
+
],
|
| 269 |
+
"min": [
|
| 270 |
+
0.35277295112609863,
|
| 271 |
+
-3.641430377960205,
|
| 272 |
+
-1.842738389968872
|
| 273 |
+
],
|
| 274 |
+
"mean": [
|
| 275 |
+
2.9722166336668394,
|
| 276 |
+
-0.2204706193566303,
|
| 277 |
+
-0.12557939087348713
|
| 278 |
+
],
|
| 279 |
+
"std": [
|
| 280 |
+
0.34427400088135357,
|
| 281 |
+
0.9069425374402487,
|
| 282 |
+
0.3253894190906973
|
| 283 |
+
],
|
| 284 |
+
"q01": [
|
| 285 |
+
1.3085840785503386,
|
| 286 |
+
-2.886677579879761,
|
| 287 |
+
-1.1599004411697387
|
| 288 |
+
],
|
| 289 |
+
"q99": [
|
| 290 |
+
3.303542451858519,
|
| 291 |
+
2.7496529006957933,
|
| 292 |
+
0.6893712210655194
|
| 293 |
+
]
|
| 294 |
+
},
|
| 295 |
+
"eef_position": {
|
| 296 |
+
"max": [
|
| 297 |
+
0.21031762659549713,
|
| 298 |
+
0.39128610491752625,
|
| 299 |
+
1.3660105466842651
|
| 300 |
+
],
|
| 301 |
+
"min": [
|
| 302 |
+
-0.4828203022480011,
|
| 303 |
+
-0.3255046010017395,
|
| 304 |
+
0.008128180168569088
|
| 305 |
+
],
|
| 306 |
+
"mean": [
|
| 307 |
+
-0.04651873600711691,
|
| 308 |
+
0.03440890975831591,
|
| 309 |
+
0.764557162431748
|
| 310 |
+
],
|
| 311 |
+
"std": [
|
| 312 |
+
0.1049434680444918,
|
| 313 |
+
0.15176550924794815,
|
| 314 |
+
0.3785180284398934
|
| 315 |
+
],
|
| 316 |
+
"q01": [
|
| 317 |
+
-0.42401049643754957,
|
| 318 |
+
-0.2838300323486328,
|
| 319 |
+
0.009925739830359817
|
| 320 |
+
],
|
| 321 |
+
"q99": [
|
| 322 |
+
0.1530261474847791,
|
| 323 |
+
0.362916499376297,
|
| 324 |
+
1.2910678112506866
|
| 325 |
+
]
|
| 326 |
+
},
|
| 327 |
+
"libero_gripper_position": {
|
| 328 |
+
"max": [
|
| 329 |
+
0.04233968257904053,
|
| 330 |
+
0.0013633022317662835
|
| 331 |
+
],
|
| 332 |
+
"min": [
|
| 333 |
+
-0.0013586411951109767,
|
| 334 |
+
-0.042040832340717316
|
| 335 |
+
],
|
| 336 |
+
"mean": [
|
| 337 |
+
0.02691481335898233,
|
| 338 |
+
-0.02719087286926901
|
| 339 |
+
],
|
| 340 |
+
"std": [
|
| 341 |
+
0.01417594365797819,
|
| 342 |
+
0.014058877749021296
|
| 343 |
+
],
|
| 344 |
+
"q01": [
|
| 345 |
+
0.001503719249740243,
|
| 346 |
+
-0.040336399003863335
|
| 347 |
+
],
|
| 348 |
+
"q99": [
|
| 349 |
+
0.040610933862626555,
|
| 350 |
+
-0.0015016929572448147
|
| 351 |
+
]
|
| 352 |
+
}
|
| 353 |
+
},
|
| 354 |
+
"action": {
|
| 355 |
+
"eef_position": {
|
| 356 |
+
"max": [
|
| 357 |
+
0.9375,
|
| 358 |
+
0.9375,
|
| 359 |
+
0.9375
|
| 360 |
+
],
|
| 361 |
+
"min": [
|
| 362 |
+
-0.9375,
|
| 363 |
+
-0.9375,
|
| 364 |
+
-0.9375
|
| 365 |
+
],
|
| 366 |
+
"mean": [
|
| 367 |
+
0.06278154433021929,
|
| 368 |
+
0.08684070332300477,
|
| 369 |
+
-0.09037311599203464
|
| 370 |
+
],
|
| 371 |
+
"std": [
|
| 372 |
+
0.3355340671542141,
|
| 373 |
+
0.3784624131392225,
|
| 374 |
+
0.44472251877152186
|
| 375 |
+
],
|
| 376 |
+
"q01": [
|
| 377 |
+
-0.8785714507102966,
|
| 378 |
+
-0.8758928775787354,
|
| 379 |
+
-0.9375
|
| 380 |
+
],
|
| 381 |
+
"q99": [
|
| 382 |
+
0.9375,
|
| 383 |
+
0.9107142686843872,
|
| 384 |
+
0.9375
|
| 385 |
+
]
|
| 386 |
+
},
|
| 387 |
+
"eef_rotation": {
|
| 388 |
+
"max": [
|
| 389 |
+
0.3557142913341522,
|
| 390 |
+
0.375,
|
| 391 |
+
0.375
|
| 392 |
+
],
|
| 393 |
+
"min": [
|
| 394 |
+
-0.2582142949104309,
|
| 395 |
+
-0.375,
|
| 396 |
+
-0.3675000071525574
|
| 397 |
+
],
|
| 398 |
+
"mean": [
|
| 399 |
+
0.0005407439826102575,
|
| 400 |
+
0.005643430440568553,
|
| 401 |
+
-0.005229132451837535
|
| 402 |
+
],
|
| 403 |
+
"std": [
|
| 404 |
+
0.039242784623089826,
|
| 405 |
+
0.06339272159958631,
|
| 406 |
+
0.077975367145476
|
| 407 |
+
],
|
| 408 |
+
"q01": [
|
| 409 |
+
-0.1510714292526245,
|
| 410 |
+
-0.20678570866584778,
|
| 411 |
+
-0.2742857038974762
|
| 412 |
+
],
|
| 413 |
+
"q99": [
|
| 414 |
+
0.20357142388820648,
|
| 415 |
+
0.26357144117355347,
|
| 416 |
+
0.375
|
| 417 |
+
]
|
| 418 |
+
},
|
| 419 |
+
"gripper_position": {
|
| 420 |
+
"max": [
|
| 421 |
+
1.0
|
| 422 |
+
],
|
| 423 |
+
"min": [
|
| 424 |
+
0.0
|
| 425 |
+
],
|
| 426 |
+
"mean": [
|
| 427 |
+
0.5248203610828128
|
| 428 |
+
],
|
| 429 |
+
"std": [
|
| 430 |
+
0.4994850167690421
|
| 431 |
+
],
|
| 432 |
+
"q01": [
|
| 433 |
+
0.0
|
| 434 |
+
],
|
| 435 |
+
"q99": [
|
| 436 |
+
1.0
|
| 437 |
+
]
|
| 438 |
+
}
|
| 439 |
+
}
|
| 440 |
+
},
|
| 441 |
+
"modalities": {
|
| 442 |
+
"video": {
|
| 443 |
+
"top_view": {
|
| 444 |
+
"resolution": [
|
| 445 |
+
256,
|
| 446 |
+
256
|
| 447 |
+
],
|
| 448 |
+
"channels": 3,
|
| 449 |
+
"fps": 20.0
|
| 450 |
+
},
|
| 451 |
+
"wrist_view": {
|
| 452 |
+
"resolution": [
|
| 453 |
+
256,
|
| 454 |
+
256
|
| 455 |
+
],
|
| 456 |
+
"channels": 3,
|
| 457 |
+
"fps": 20.0
|
| 458 |
+
}
|
| 459 |
+
},
|
| 460 |
+
"state": {
|
| 461 |
+
"eef_position": {
|
| 462 |
+
"absolute": true,
|
| 463 |
+
"rotation_type": null,
|
| 464 |
+
"shape": [
|
| 465 |
+
3
|
| 466 |
+
],
|
| 467 |
+
"continuous": true
|
| 468 |
+
},
|
| 469 |
+
"eef_rotation": {
|
| 470 |
+
"absolute": true,
|
| 471 |
+
"rotation_type": "axis_angle",
|
| 472 |
+
"shape": [
|
| 473 |
+
3
|
| 474 |
+
],
|
| 475 |
+
"continuous": true
|
| 476 |
+
},
|
| 477 |
+
"libero_gripper_position": {
|
| 478 |
+
"absolute": true,
|
| 479 |
+
"rotation_type": null,
|
| 480 |
+
"shape": [
|
| 481 |
+
2
|
| 482 |
+
],
|
| 483 |
+
"continuous": true
|
| 484 |
+
}
|
| 485 |
+
},
|
| 486 |
+
"action": {
|
| 487 |
+
"eef_position": {
|
| 488 |
+
"absolute": false,
|
| 489 |
+
"rotation_type": null,
|
| 490 |
+
"shape": [
|
| 491 |
+
3
|
| 492 |
+
],
|
| 493 |
+
"continuous": true
|
| 494 |
+
},
|
| 495 |
+
"eef_rotation": {
|
| 496 |
+
"absolute": false,
|
| 497 |
+
"rotation_type": "axis_angle",
|
| 498 |
+
"shape": [
|
| 499 |
+
3
|
| 500 |
+
],
|
| 501 |
+
"continuous": true
|
| 502 |
+
},
|
| 503 |
+
"gripper_position": {
|
| 504 |
+
"absolute": true,
|
| 505 |
+
"rotation_type": null,
|
| 506 |
+
"shape": [
|
| 507 |
+
1
|
| 508 |
+
],
|
| 509 |
+
"continuous": true
|
| 510 |
+
}
|
| 511 |
+
}
|
| 512 |
+
},
|
| 513 |
+
"embodiment_tag": "new_embodiment",
|
| 514 |
+
"stats_level": "task"
|
| 515 |
+
},
|
| 516 |
+
"libero_object_no_noops_1.0.0_lerobot": {
|
| 517 |
+
"statistics": {
|
| 518 |
+
"state": {
|
| 519 |
+
"eef_rotation": {
|
| 520 |
+
"max": [
|
| 521 |
+
3.6714255809783936,
|
| 522 |
+
3.560650587081909,
|
| 523 |
+
1.386339545249939
|
| 524 |
+
],
|
| 525 |
+
"min": [
|
| 526 |
+
0.35277295112609863,
|
| 527 |
+
-3.641430377960205,
|
| 528 |
+
-1.842738389968872
|
| 529 |
+
],
|
| 530 |
+
"mean": [
|
| 531 |
+
2.9722166336668394,
|
| 532 |
+
-0.2204706193566303,
|
| 533 |
+
-0.12557939087348713
|
| 534 |
+
],
|
| 535 |
+
"std": [
|
| 536 |
+
0.34427400088135357,
|
| 537 |
+
0.9069425374402487,
|
| 538 |
+
0.3253894190906973
|
| 539 |
+
],
|
| 540 |
+
"q01": [
|
| 541 |
+
1.3085840785503386,
|
| 542 |
+
-2.886677579879761,
|
| 543 |
+
-1.1599004411697387
|
| 544 |
+
],
|
| 545 |
+
"q99": [
|
| 546 |
+
3.303542451858519,
|
| 547 |
+
2.7496529006957933,
|
| 548 |
+
0.6893712210655194
|
| 549 |
+
]
|
| 550 |
+
},
|
| 551 |
+
"eef_position": {
|
| 552 |
+
"max": [
|
| 553 |
+
0.21031762659549713,
|
| 554 |
+
0.39128610491752625,
|
| 555 |
+
1.3660105466842651
|
| 556 |
+
],
|
| 557 |
+
"min": [
|
| 558 |
+
-0.4828203022480011,
|
| 559 |
+
-0.3255046010017395,
|
| 560 |
+
0.008128180168569088
|
| 561 |
+
],
|
| 562 |
+
"mean": [
|
| 563 |
+
-0.04651873600711691,
|
| 564 |
+
0.03440890975831591,
|
| 565 |
+
0.764557162431748
|
| 566 |
+
],
|
| 567 |
+
"std": [
|
| 568 |
+
0.1049434680444918,
|
| 569 |
+
0.15176550924794815,
|
| 570 |
+
0.3785180284398934
|
| 571 |
+
],
|
| 572 |
+
"q01": [
|
| 573 |
+
-0.42401049643754957,
|
| 574 |
+
-0.2838300323486328,
|
| 575 |
+
0.009925739830359817
|
| 576 |
+
],
|
| 577 |
+
"q99": [
|
| 578 |
+
0.1530261474847791,
|
| 579 |
+
0.362916499376297,
|
| 580 |
+
1.2910678112506866
|
| 581 |
+
]
|
| 582 |
+
},
|
| 583 |
+
"libero_gripper_position": {
|
| 584 |
+
"max": [
|
| 585 |
+
0.04233968257904053,
|
| 586 |
+
0.0013633022317662835
|
| 587 |
+
],
|
| 588 |
+
"min": [
|
| 589 |
+
-0.0013586411951109767,
|
| 590 |
+
-0.042040832340717316
|
| 591 |
+
],
|
| 592 |
+
"mean": [
|
| 593 |
+
0.02691481335898233,
|
| 594 |
+
-0.02719087286926901
|
| 595 |
+
],
|
| 596 |
+
"std": [
|
| 597 |
+
0.01417594365797819,
|
| 598 |
+
0.014058877749021296
|
| 599 |
+
],
|
| 600 |
+
"q01": [
|
| 601 |
+
0.001503719249740243,
|
| 602 |
+
-0.040336399003863335
|
| 603 |
+
],
|
| 604 |
+
"q99": [
|
| 605 |
+
0.040610933862626555,
|
| 606 |
+
-0.0015016929572448147
|
| 607 |
+
]
|
| 608 |
+
}
|
| 609 |
+
},
|
| 610 |
+
"action": {
|
| 611 |
+
"eef_position": {
|
| 612 |
+
"max": [
|
| 613 |
+
0.9375,
|
| 614 |
+
0.9375,
|
| 615 |
+
0.9375
|
| 616 |
+
],
|
| 617 |
+
"min": [
|
| 618 |
+
-0.9375,
|
| 619 |
+
-0.9375,
|
| 620 |
+
-0.9375
|
| 621 |
+
],
|
| 622 |
+
"mean": [
|
| 623 |
+
0.06278154433021929,
|
| 624 |
+
0.08684070332300477,
|
| 625 |
+
-0.09037311599203464
|
| 626 |
+
],
|
| 627 |
+
"std": [
|
| 628 |
+
0.3355340671542141,
|
| 629 |
+
0.3784624131392225,
|
| 630 |
+
0.44472251877152186
|
| 631 |
+
],
|
| 632 |
+
"q01": [
|
| 633 |
+
-0.8785714507102966,
|
| 634 |
+
-0.8758928775787354,
|
| 635 |
+
-0.9375
|
| 636 |
+
],
|
| 637 |
+
"q99": [
|
| 638 |
+
0.9375,
|
| 639 |
+
0.9107142686843872,
|
| 640 |
+
0.9375
|
| 641 |
+
]
|
| 642 |
+
},
|
| 643 |
+
"eef_rotation": {
|
| 644 |
+
"max": [
|
| 645 |
+
0.3557142913341522,
|
| 646 |
+
0.375,
|
| 647 |
+
0.375
|
| 648 |
+
],
|
| 649 |
+
"min": [
|
| 650 |
+
-0.2582142949104309,
|
| 651 |
+
-0.375,
|
| 652 |
+
-0.3675000071525574
|
| 653 |
+
],
|
| 654 |
+
"mean": [
|
| 655 |
+
0.0005407439826102575,
|
| 656 |
+
0.005643430440568553,
|
| 657 |
+
-0.005229132451837535
|
| 658 |
+
],
|
| 659 |
+
"std": [
|
| 660 |
+
0.039242784623089826,
|
| 661 |
+
0.06339272159958631,
|
| 662 |
+
0.077975367145476
|
| 663 |
+
],
|
| 664 |
+
"q01": [
|
| 665 |
+
-0.1510714292526245,
|
| 666 |
+
-0.20678570866584778,
|
| 667 |
+
-0.2742857038974762
|
| 668 |
+
],
|
| 669 |
+
"q99": [
|
| 670 |
+
0.20357142388820648,
|
| 671 |
+
0.26357144117355347,
|
| 672 |
+
0.375
|
| 673 |
+
]
|
| 674 |
+
},
|
| 675 |
+
"gripper_position": {
|
| 676 |
+
"max": [
|
| 677 |
+
1.0
|
| 678 |
+
],
|
| 679 |
+
"min": [
|
| 680 |
+
0.0
|
| 681 |
+
],
|
| 682 |
+
"mean": [
|
| 683 |
+
0.5248203610828128
|
| 684 |
+
],
|
| 685 |
+
"std": [
|
| 686 |
+
0.4994850167690421
|
| 687 |
+
],
|
| 688 |
+
"q01": [
|
| 689 |
+
0.0
|
| 690 |
+
],
|
| 691 |
+
"q99": [
|
| 692 |
+
1.0
|
| 693 |
+
]
|
| 694 |
+
}
|
| 695 |
+
}
|
| 696 |
+
},
|
| 697 |
+
"modalities": {
|
| 698 |
+
"video": {
|
| 699 |
+
"top_view": {
|
| 700 |
+
"resolution": [
|
| 701 |
+
256,
|
| 702 |
+
256
|
| 703 |
+
],
|
| 704 |
+
"channels": 3,
|
| 705 |
+
"fps": 20.0
|
| 706 |
+
},
|
| 707 |
+
"wrist_view": {
|
| 708 |
+
"resolution": [
|
| 709 |
+
256,
|
| 710 |
+
256
|
| 711 |
+
],
|
| 712 |
+
"channels": 3,
|
| 713 |
+
"fps": 20.0
|
| 714 |
+
}
|
| 715 |
+
},
|
| 716 |
+
"state": {
|
| 717 |
+
"eef_position": {
|
| 718 |
+
"absolute": true,
|
| 719 |
+
"rotation_type": null,
|
| 720 |
+
"shape": [
|
| 721 |
+
3
|
| 722 |
+
],
|
| 723 |
+
"continuous": true
|
| 724 |
+
},
|
| 725 |
+
"eef_rotation": {
|
| 726 |
+
"absolute": true,
|
| 727 |
+
"rotation_type": "axis_angle",
|
| 728 |
+
"shape": [
|
| 729 |
+
3
|
| 730 |
+
],
|
| 731 |
+
"continuous": true
|
| 732 |
+
},
|
| 733 |
+
"libero_gripper_position": {
|
| 734 |
+
"absolute": true,
|
| 735 |
+
"rotation_type": null,
|
| 736 |
+
"shape": [
|
| 737 |
+
2
|
| 738 |
+
],
|
| 739 |
+
"continuous": true
|
| 740 |
+
}
|
| 741 |
+
},
|
| 742 |
+
"action": {
|
| 743 |
+
"eef_position": {
|
| 744 |
+
"absolute": false,
|
| 745 |
+
"rotation_type": null,
|
| 746 |
+
"shape": [
|
| 747 |
+
3
|
| 748 |
+
],
|
| 749 |
+
"continuous": true
|
| 750 |
+
},
|
| 751 |
+
"eef_rotation": {
|
| 752 |
+
"absolute": false,
|
| 753 |
+
"rotation_type": "axis_angle",
|
| 754 |
+
"shape": [
|
| 755 |
+
3
|
| 756 |
+
],
|
| 757 |
+
"continuous": true
|
| 758 |
+
},
|
| 759 |
+
"gripper_position": {
|
| 760 |
+
"absolute": true,
|
| 761 |
+
"rotation_type": null,
|
| 762 |
+
"shape": [
|
| 763 |
+
1
|
| 764 |
+
],
|
| 765 |
+
"continuous": true
|
| 766 |
+
}
|
| 767 |
+
}
|
| 768 |
+
},
|
| 769 |
+
"embodiment_tag": "new_embodiment",
|
| 770 |
+
"stats_level": "task"
|
| 771 |
+
},
|
| 772 |
+
"libero_goal_no_noops_1.0.0_lerobot": {
|
| 773 |
+
"statistics": {
|
| 774 |
+
"state": {
|
| 775 |
+
"eef_rotation": {
|
| 776 |
+
"max": [
|
| 777 |
+
3.6714255809783936,
|
| 778 |
+
3.560650587081909,
|
| 779 |
+
1.386339545249939
|
| 780 |
+
],
|
| 781 |
+
"min": [
|
| 782 |
+
0.35277295112609863,
|
| 783 |
+
-3.641430377960205,
|
| 784 |
+
-1.842738389968872
|
| 785 |
+
],
|
| 786 |
+
"mean": [
|
| 787 |
+
2.9722166336668394,
|
| 788 |
+
-0.2204706193566303,
|
| 789 |
+
-0.12557939087348713
|
| 790 |
+
],
|
| 791 |
+
"std": [
|
| 792 |
+
0.34427400088135357,
|
| 793 |
+
0.9069425374402487,
|
| 794 |
+
0.3253894190906973
|
| 795 |
+
],
|
| 796 |
+
"q01": [
|
| 797 |
+
1.3085840785503386,
|
| 798 |
+
-2.886677579879761,
|
| 799 |
+
-1.1599004411697387
|
| 800 |
+
],
|
| 801 |
+
"q99": [
|
| 802 |
+
3.303542451858519,
|
| 803 |
+
2.7496529006957933,
|
| 804 |
+
0.6893712210655194
|
| 805 |
+
]
|
| 806 |
+
},
|
| 807 |
+
"eef_position": {
|
| 808 |
+
"max": [
|
| 809 |
+
0.21031762659549713,
|
| 810 |
+
0.39128610491752625,
|
| 811 |
+
1.3660105466842651
|
| 812 |
+
],
|
| 813 |
+
"min": [
|
| 814 |
+
-0.4828203022480011,
|
| 815 |
+
-0.3255046010017395,
|
| 816 |
+
0.008128180168569088
|
| 817 |
+
],
|
| 818 |
+
"mean": [
|
| 819 |
+
-0.04651873600711691,
|
| 820 |
+
0.03440890975831591,
|
| 821 |
+
0.764557162431748
|
| 822 |
+
],
|
| 823 |
+
"std": [
|
| 824 |
+
0.1049434680444918,
|
| 825 |
+
0.15176550924794815,
|
| 826 |
+
0.3785180284398934
|
| 827 |
+
],
|
| 828 |
+
"q01": [
|
| 829 |
+
-0.42401049643754957,
|
| 830 |
+
-0.2838300323486328,
|
| 831 |
+
0.009925739830359817
|
| 832 |
+
],
|
| 833 |
+
"q99": [
|
| 834 |
+
0.1530261474847791,
|
| 835 |
+
0.362916499376297,
|
| 836 |
+
1.2910678112506866
|
| 837 |
+
]
|
| 838 |
+
},
|
| 839 |
+
"libero_gripper_position": {
|
| 840 |
+
"max": [
|
| 841 |
+
0.04233968257904053,
|
| 842 |
+
0.0013633022317662835
|
| 843 |
+
],
|
| 844 |
+
"min": [
|
| 845 |
+
-0.0013586411951109767,
|
| 846 |
+
-0.042040832340717316
|
| 847 |
+
],
|
| 848 |
+
"mean": [
|
| 849 |
+
0.02691481335898233,
|
| 850 |
+
-0.02719087286926901
|
| 851 |
+
],
|
| 852 |
+
"std": [
|
| 853 |
+
0.01417594365797819,
|
| 854 |
+
0.014058877749021296
|
| 855 |
+
],
|
| 856 |
+
"q01": [
|
| 857 |
+
0.001503719249740243,
|
| 858 |
+
-0.040336399003863335
|
| 859 |
+
],
|
| 860 |
+
"q99": [
|
| 861 |
+
0.040610933862626555,
|
| 862 |
+
-0.0015016929572448147
|
| 863 |
+
]
|
| 864 |
+
}
|
| 865 |
+
},
|
| 866 |
+
"action": {
|
| 867 |
+
"eef_position": {
|
| 868 |
+
"max": [
|
| 869 |
+
0.9375,
|
| 870 |
+
0.9375,
|
| 871 |
+
0.9375
|
| 872 |
+
],
|
| 873 |
+
"min": [
|
| 874 |
+
-0.9375,
|
| 875 |
+
-0.9375,
|
| 876 |
+
-0.9375
|
| 877 |
+
],
|
| 878 |
+
"mean": [
|
| 879 |
+
0.06278154433021929,
|
| 880 |
+
0.08684070332300477,
|
| 881 |
+
-0.09037311599203464
|
| 882 |
+
],
|
| 883 |
+
"std": [
|
| 884 |
+
0.3355340671542141,
|
| 885 |
+
0.3784624131392225,
|
| 886 |
+
0.44472251877152186
|
| 887 |
+
],
|
| 888 |
+
"q01": [
|
| 889 |
+
-0.8785714507102966,
|
| 890 |
+
-0.8758928775787354,
|
| 891 |
+
-0.9375
|
| 892 |
+
],
|
| 893 |
+
"q99": [
|
| 894 |
+
0.9375,
|
| 895 |
+
0.9107142686843872,
|
| 896 |
+
0.9375
|
| 897 |
+
]
|
| 898 |
+
},
|
| 899 |
+
"eef_rotation": {
|
| 900 |
+
"max": [
|
| 901 |
+
0.3557142913341522,
|
| 902 |
+
0.375,
|
| 903 |
+
0.375
|
| 904 |
+
],
|
| 905 |
+
"min": [
|
| 906 |
+
-0.2582142949104309,
|
| 907 |
+
-0.375,
|
| 908 |
+
-0.3675000071525574
|
| 909 |
+
],
|
| 910 |
+
"mean": [
|
| 911 |
+
0.0005407439826102575,
|
| 912 |
+
0.005643430440568553,
|
| 913 |
+
-0.005229132451837535
|
| 914 |
+
],
|
| 915 |
+
"std": [
|
| 916 |
+
0.039242784623089826,
|
| 917 |
+
0.06339272159958631,
|
| 918 |
+
0.077975367145476
|
| 919 |
+
],
|
| 920 |
+
"q01": [
|
| 921 |
+
-0.1510714292526245,
|
| 922 |
+
-0.20678570866584778,
|
| 923 |
+
-0.2742857038974762
|
| 924 |
+
],
|
| 925 |
+
"q99": [
|
| 926 |
+
0.20357142388820648,
|
| 927 |
+
0.26357144117355347,
|
| 928 |
+
0.375
|
| 929 |
+
]
|
| 930 |
+
},
|
| 931 |
+
"gripper_position": {
|
| 932 |
+
"max": [
|
| 933 |
+
1.0
|
| 934 |
+
],
|
| 935 |
+
"min": [
|
| 936 |
+
0.0
|
| 937 |
+
],
|
| 938 |
+
"mean": [
|
| 939 |
+
0.5248203610828128
|
| 940 |
+
],
|
| 941 |
+
"std": [
|
| 942 |
+
0.4994850167690421
|
| 943 |
+
],
|
| 944 |
+
"q01": [
|
| 945 |
+
0.0
|
| 946 |
+
],
|
| 947 |
+
"q99": [
|
| 948 |
+
1.0
|
| 949 |
+
]
|
| 950 |
+
}
|
| 951 |
+
}
|
| 952 |
+
},
|
| 953 |
+
"modalities": {
|
| 954 |
+
"video": {
|
| 955 |
+
"top_view": {
|
| 956 |
+
"resolution": [
|
| 957 |
+
256,
|
| 958 |
+
256
|
| 959 |
+
],
|
| 960 |
+
"channels": 3,
|
| 961 |
+
"fps": 20.0
|
| 962 |
+
},
|
| 963 |
+
"wrist_view": {
|
| 964 |
+
"resolution": [
|
| 965 |
+
256,
|
| 966 |
+
256
|
| 967 |
+
],
|
| 968 |
+
"channels": 3,
|
| 969 |
+
"fps": 20.0
|
| 970 |
+
}
|
| 971 |
+
},
|
| 972 |
+
"state": {
|
| 973 |
+
"eef_position": {
|
| 974 |
+
"absolute": true,
|
| 975 |
+
"rotation_type": null,
|
| 976 |
+
"shape": [
|
| 977 |
+
3
|
| 978 |
+
],
|
| 979 |
+
"continuous": true
|
| 980 |
+
},
|
| 981 |
+
"eef_rotation": {
|
| 982 |
+
"absolute": true,
|
| 983 |
+
"rotation_type": "axis_angle",
|
| 984 |
+
"shape": [
|
| 985 |
+
3
|
| 986 |
+
],
|
| 987 |
+
"continuous": true
|
| 988 |
+
},
|
| 989 |
+
"libero_gripper_position": {
|
| 990 |
+
"absolute": true,
|
| 991 |
+
"rotation_type": null,
|
| 992 |
+
"shape": [
|
| 993 |
+
2
|
| 994 |
+
],
|
| 995 |
+
"continuous": true
|
| 996 |
+
}
|
| 997 |
+
},
|
| 998 |
+
"action": {
|
| 999 |
+
"eef_position": {
|
| 1000 |
+
"absolute": false,
|
| 1001 |
+
"rotation_type": null,
|
| 1002 |
+
"shape": [
|
| 1003 |
+
3
|
| 1004 |
+
],
|
| 1005 |
+
"continuous": true
|
| 1006 |
+
},
|
| 1007 |
+
"eef_rotation": {
|
| 1008 |
+
"absolute": false,
|
| 1009 |
+
"rotation_type": "axis_angle",
|
| 1010 |
+
"shape": [
|
| 1011 |
+
3
|
| 1012 |
+
],
|
| 1013 |
+
"continuous": true
|
| 1014 |
+
},
|
| 1015 |
+
"gripper_position": {
|
| 1016 |
+
"absolute": true,
|
| 1017 |
+
"rotation_type": null,
|
| 1018 |
+
"shape": [
|
| 1019 |
+
1
|
| 1020 |
+
],
|
| 1021 |
+
"continuous": true
|
| 1022 |
+
}
|
| 1023 |
+
}
|
| 1024 |
+
},
|
| 1025 |
+
"embodiment_tag": "new_embodiment",
|
| 1026 |
+
"stats_level": "task"
|
| 1027 |
+
},
|
| 1028 |
+
"libero_10_no_noops_1.0.0_lerobot": {
|
| 1029 |
+
"statistics": {
|
| 1030 |
+
"state": {
|
| 1031 |
+
"eef_rotation": {
|
| 1032 |
+
"max": [
|
| 1033 |
+
3.6714255809783936,
|
| 1034 |
+
3.560650587081909,
|
| 1035 |
+
1.386339545249939
|
| 1036 |
+
],
|
| 1037 |
+
"min": [
|
| 1038 |
+
0.35277295112609863,
|
| 1039 |
+
-3.641430377960205,
|
| 1040 |
+
-1.842738389968872
|
| 1041 |
+
],
|
| 1042 |
+
"mean": [
|
| 1043 |
+
2.9722166336668394,
|
| 1044 |
+
-0.2204706193566303,
|
| 1045 |
+
-0.12557939087348713
|
| 1046 |
+
],
|
| 1047 |
+
"std": [
|
| 1048 |
+
0.34427400088135357,
|
| 1049 |
+
0.9069425374402487,
|
| 1050 |
+
0.3253894190906973
|
| 1051 |
+
],
|
| 1052 |
+
"q01": [
|
| 1053 |
+
1.3085840785503386,
|
| 1054 |
+
-2.886677579879761,
|
| 1055 |
+
-1.1599004411697387
|
| 1056 |
+
],
|
| 1057 |
+
"q99": [
|
| 1058 |
+
3.303542451858519,
|
| 1059 |
+
2.7496529006957933,
|
| 1060 |
+
0.6893712210655194
|
| 1061 |
+
]
|
| 1062 |
+
},
|
| 1063 |
+
"eef_position": {
|
| 1064 |
+
"max": [
|
| 1065 |
+
0.21031762659549713,
|
| 1066 |
+
0.39128610491752625,
|
| 1067 |
+
1.3660105466842651
|
| 1068 |
+
],
|
| 1069 |
+
"min": [
|
| 1070 |
+
-0.4828203022480011,
|
| 1071 |
+
-0.3255046010017395,
|
| 1072 |
+
0.008128180168569088
|
| 1073 |
+
],
|
| 1074 |
+
"mean": [
|
| 1075 |
+
-0.04651873600711691,
|
| 1076 |
+
0.03440890975831591,
|
| 1077 |
+
0.764557162431748
|
| 1078 |
+
],
|
| 1079 |
+
"std": [
|
| 1080 |
+
0.1049434680444918,
|
| 1081 |
+
0.15176550924794815,
|
| 1082 |
+
0.3785180284398934
|
| 1083 |
+
],
|
| 1084 |
+
"q01": [
|
| 1085 |
+
-0.42401049643754957,
|
| 1086 |
+
-0.2838300323486328,
|
| 1087 |
+
0.009925739830359817
|
| 1088 |
+
],
|
| 1089 |
+
"q99": [
|
| 1090 |
+
0.1530261474847791,
|
| 1091 |
+
0.362916499376297,
|
| 1092 |
+
1.2910678112506866
|
| 1093 |
+
]
|
| 1094 |
+
},
|
| 1095 |
+
"libero_gripper_position": {
|
| 1096 |
+
"max": [
|
| 1097 |
+
0.04233968257904053,
|
| 1098 |
+
0.0013633022317662835
|
| 1099 |
+
],
|
| 1100 |
+
"min": [
|
| 1101 |
+
-0.0013586411951109767,
|
| 1102 |
+
-0.042040832340717316
|
| 1103 |
+
],
|
| 1104 |
+
"mean": [
|
| 1105 |
+
0.02691481335898233,
|
| 1106 |
+
-0.02719087286926901
|
| 1107 |
+
],
|
| 1108 |
+
"std": [
|
| 1109 |
+
0.01417594365797819,
|
| 1110 |
+
0.014058877749021296
|
| 1111 |
+
],
|
| 1112 |
+
"q01": [
|
| 1113 |
+
0.001503719249740243,
|
| 1114 |
+
-0.040336399003863335
|
| 1115 |
+
],
|
| 1116 |
+
"q99": [
|
| 1117 |
+
0.040610933862626555,
|
| 1118 |
+
-0.0015016929572448147
|
| 1119 |
+
]
|
| 1120 |
+
}
|
| 1121 |
+
},
|
| 1122 |
+
"action": {
|
| 1123 |
+
"eef_position": {
|
| 1124 |
+
"max": [
|
| 1125 |
+
0.9375,
|
| 1126 |
+
0.9375,
|
| 1127 |
+
0.9375
|
| 1128 |
+
],
|
| 1129 |
+
"min": [
|
| 1130 |
+
-0.9375,
|
| 1131 |
+
-0.9375,
|
| 1132 |
+
-0.9375
|
| 1133 |
+
],
|
| 1134 |
+
"mean": [
|
| 1135 |
+
0.06278154433021929,
|
| 1136 |
+
0.08684070332300477,
|
| 1137 |
+
-0.09037311599203464
|
| 1138 |
+
],
|
| 1139 |
+
"std": [
|
| 1140 |
+
0.3355340671542141,
|
| 1141 |
+
0.3784624131392225,
|
| 1142 |
+
0.44472251877152186
|
| 1143 |
+
],
|
| 1144 |
+
"q01": [
|
| 1145 |
+
-0.8785714507102966,
|
| 1146 |
+
-0.8758928775787354,
|
| 1147 |
+
-0.9375
|
| 1148 |
+
],
|
| 1149 |
+
"q99": [
|
| 1150 |
+
0.9375,
|
| 1151 |
+
0.9107142686843872,
|
| 1152 |
+
0.9375
|
| 1153 |
+
]
|
| 1154 |
+
},
|
| 1155 |
+
"eef_rotation": {
|
| 1156 |
+
"max": [
|
| 1157 |
+
0.3557142913341522,
|
| 1158 |
+
0.375,
|
| 1159 |
+
0.375
|
| 1160 |
+
],
|
| 1161 |
+
"min": [
|
| 1162 |
+
-0.2582142949104309,
|
| 1163 |
+
-0.375,
|
| 1164 |
+
-0.3675000071525574
|
| 1165 |
+
],
|
| 1166 |
+
"mean": [
|
| 1167 |
+
0.0005407439826102575,
|
| 1168 |
+
0.005643430440568553,
|
| 1169 |
+
-0.005229132451837535
|
| 1170 |
+
],
|
| 1171 |
+
"std": [
|
| 1172 |
+
0.039242784623089826,
|
| 1173 |
+
0.06339272159958631,
|
| 1174 |
+
0.077975367145476
|
| 1175 |
+
],
|
| 1176 |
+
"q01": [
|
| 1177 |
+
-0.1510714292526245,
|
| 1178 |
+
-0.20678570866584778,
|
| 1179 |
+
-0.2742857038974762
|
| 1180 |
+
],
|
| 1181 |
+
"q99": [
|
| 1182 |
+
0.20357142388820648,
|
| 1183 |
+
0.26357144117355347,
|
| 1184 |
+
0.375
|
| 1185 |
+
]
|
| 1186 |
+
},
|
| 1187 |
+
"gripper_position": {
|
| 1188 |
+
"max": [
|
| 1189 |
+
1.0
|
| 1190 |
+
],
|
| 1191 |
+
"min": [
|
| 1192 |
+
0.0
|
| 1193 |
+
],
|
| 1194 |
+
"mean": [
|
| 1195 |
+
0.5248203610828128
|
| 1196 |
+
],
|
| 1197 |
+
"std": [
|
| 1198 |
+
0.4994850167690421
|
| 1199 |
+
],
|
| 1200 |
+
"q01": [
|
| 1201 |
+
0.0
|
| 1202 |
+
],
|
| 1203 |
+
"q99": [
|
| 1204 |
+
1.0
|
| 1205 |
+
]
|
| 1206 |
+
}
|
| 1207 |
+
}
|
| 1208 |
+
},
|
| 1209 |
+
"modalities": {
|
| 1210 |
+
"video": {
|
| 1211 |
+
"top_view": {
|
| 1212 |
+
"resolution": [
|
| 1213 |
+
256,
|
| 1214 |
+
256
|
| 1215 |
+
],
|
| 1216 |
+
"channels": 3,
|
| 1217 |
+
"fps": 20.0
|
| 1218 |
+
},
|
| 1219 |
+
"wrist_view": {
|
| 1220 |
+
"resolution": [
|
| 1221 |
+
256,
|
| 1222 |
+
256
|
| 1223 |
+
],
|
| 1224 |
+
"channels": 3,
|
| 1225 |
+
"fps": 20.0
|
| 1226 |
+
}
|
| 1227 |
+
},
|
| 1228 |
+
"state": {
|
| 1229 |
+
"eef_position": {
|
| 1230 |
+
"absolute": true,
|
| 1231 |
+
"rotation_type": null,
|
| 1232 |
+
"shape": [
|
| 1233 |
+
3
|
| 1234 |
+
],
|
| 1235 |
+
"continuous": true
|
| 1236 |
+
},
|
| 1237 |
+
"eef_rotation": {
|
| 1238 |
+
"absolute": true,
|
| 1239 |
+
"rotation_type": "axis_angle",
|
| 1240 |
+
"shape": [
|
| 1241 |
+
3
|
| 1242 |
+
],
|
| 1243 |
+
"continuous": true
|
| 1244 |
+
},
|
| 1245 |
+
"libero_gripper_position": {
|
| 1246 |
+
"absolute": true,
|
| 1247 |
+
"rotation_type": null,
|
| 1248 |
+
"shape": [
|
| 1249 |
+
2
|
| 1250 |
+
],
|
| 1251 |
+
"continuous": true
|
| 1252 |
+
}
|
| 1253 |
+
},
|
| 1254 |
+
"action": {
|
| 1255 |
+
"eef_position": {
|
| 1256 |
+
"absolute": false,
|
| 1257 |
+
"rotation_type": null,
|
| 1258 |
+
"shape": [
|
| 1259 |
+
3
|
| 1260 |
+
],
|
| 1261 |
+
"continuous": true
|
| 1262 |
+
},
|
| 1263 |
+
"eef_rotation": {
|
| 1264 |
+
"absolute": false,
|
| 1265 |
+
"rotation_type": "axis_angle",
|
| 1266 |
+
"shape": [
|
| 1267 |
+
3
|
| 1268 |
+
],
|
| 1269 |
+
"continuous": true
|
| 1270 |
+
},
|
| 1271 |
+
"gripper_position": {
|
| 1272 |
+
"absolute": true,
|
| 1273 |
+
"rotation_type": null,
|
| 1274 |
+
"shape": [
|
| 1275 |
+
1
|
| 1276 |
+
],
|
| 1277 |
+
"continuous": true
|
| 1278 |
+
}
|
| 1279 |
+
}
|
| 1280 |
+
},
|
| 1281 |
+
"embodiment_tag": "new_embodiment",
|
| 1282 |
+
"stats_level": "task"
|
| 1283 |
+
}
|
| 1284 |
+
}
|
| 1285 |
+
}
|
libero/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
libero/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11693888257a68188bb94c110636723baa0b04a4451f07533a156e2fcab1a392
|
| 3 |
+
size 11201369880
|
libero/special_tokens_map.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>",
|
| 16 |
+
"<img>",
|
| 17 |
+
"</img>",
|
| 18 |
+
"<IMG_CONTEXT>",
|
| 19 |
+
"<quad>",
|
| 20 |
+
"</quad>",
|
| 21 |
+
"<ref>",
|
| 22 |
+
"</ref>",
|
| 23 |
+
"<box>",
|
| 24 |
+
"</box>"
|
| 25 |
+
],
|
| 26 |
+
"eos_token": {
|
| 27 |
+
"content": "<|im_end|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"pad_token": {
|
| 34 |
+
"content": "<|endoftext|>",
|
| 35 |
+
"lstrip": false,
|
| 36 |
+
"normalized": false,
|
| 37 |
+
"rstrip": false,
|
| 38 |
+
"single_word": false
|
| 39 |
+
}
|
| 40 |
+
}
|
libero/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12806c7c382822e3b8215170269ab902ff55298f14b3578a02436dde5f7c1d84
|
| 3 |
+
size 11427559
|
libero/tokenizer_config.json
ADDED
|
@@ -0,0 +1,458 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"151643": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"151644": {
|
| 15 |
+
"content": "<|im_start|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"151645": {
|
| 23 |
+
"content": "<|im_end|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"151646": {
|
| 31 |
+
"content": "<|object_ref_start|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"151647": {
|
| 39 |
+
"content": "<|object_ref_end|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"151648": {
|
| 47 |
+
"content": "<|box_start|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"151649": {
|
| 55 |
+
"content": "<|box_end|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"151650": {
|
| 63 |
+
"content": "<|quad_start|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"151651": {
|
| 71 |
+
"content": "<|quad_end|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"151652": {
|
| 79 |
+
"content": "<|vision_start|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"151653": {
|
| 87 |
+
"content": "<|vision_end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"151654": {
|
| 95 |
+
"content": "<|vision_pad|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"151655": {
|
| 103 |
+
"content": "<|image_pad|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"151656": {
|
| 111 |
+
"content": "<|video_pad|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"151657": {
|
| 119 |
+
"content": "<tool_call>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"151658": {
|
| 127 |
+
"content": "</tool_call>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"151659": {
|
| 135 |
+
"content": "<|fim_prefix|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"151660": {
|
| 143 |
+
"content": "<|fim_middle|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"151661": {
|
| 151 |
+
"content": "<|fim_suffix|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"151662": {
|
| 159 |
+
"content": "<|fim_pad|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"151663": {
|
| 167 |
+
"content": "<|repo_name|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"151664": {
|
| 175 |
+
"content": "<|file_sep|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
},
|
| 182 |
+
"151665": {
|
| 183 |
+
"content": "<tool_response>",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": false,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": false
|
| 189 |
+
},
|
| 190 |
+
"151666": {
|
| 191 |
+
"content": "</tool_response>",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": false,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": false
|
| 197 |
+
},
|
| 198 |
+
"151667": {
|
| 199 |
+
"content": "<think>",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": false
|
| 205 |
+
},
|
| 206 |
+
"151668": {
|
| 207 |
+
"content": "</think>",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": false,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false,
|
| 212 |
+
"special": false
|
| 213 |
+
},
|
| 214 |
+
"151669": {
|
| 215 |
+
"content": "<img>",
|
| 216 |
+
"lstrip": false,
|
| 217 |
+
"normalized": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"single_word": false,
|
| 220 |
+
"special": true
|
| 221 |
+
},
|
| 222 |
+
"151670": {
|
| 223 |
+
"content": "</img>",
|
| 224 |
+
"lstrip": false,
|
| 225 |
+
"normalized": false,
|
| 226 |
+
"rstrip": false,
|
| 227 |
+
"single_word": false,
|
| 228 |
+
"special": true
|
| 229 |
+
},
|
| 230 |
+
"151671": {
|
| 231 |
+
"content": "<IMG_CONTEXT>",
|
| 232 |
+
"lstrip": false,
|
| 233 |
+
"normalized": false,
|
| 234 |
+
"rstrip": false,
|
| 235 |
+
"single_word": false,
|
| 236 |
+
"special": true
|
| 237 |
+
},
|
| 238 |
+
"151672": {
|
| 239 |
+
"content": "<quad>",
|
| 240 |
+
"lstrip": false,
|
| 241 |
+
"normalized": false,
|
| 242 |
+
"rstrip": false,
|
| 243 |
+
"single_word": false,
|
| 244 |
+
"special": true
|
| 245 |
+
},
|
| 246 |
+
"151673": {
|
| 247 |
+
"content": "</quad>",
|
| 248 |
+
"lstrip": false,
|
| 249 |
+
"normalized": false,
|
| 250 |
+
"rstrip": false,
|
| 251 |
+
"single_word": false,
|
| 252 |
+
"special": true
|
| 253 |
+
},
|
| 254 |
+
"151674": {
|
| 255 |
+
"content": "<ref>",
|
| 256 |
+
"lstrip": false,
|
| 257 |
+
"normalized": false,
|
| 258 |
+
"rstrip": false,
|
| 259 |
+
"single_word": false,
|
| 260 |
+
"special": true
|
| 261 |
+
},
|
| 262 |
+
"151675": {
|
| 263 |
+
"content": "</ref>",
|
| 264 |
+
"lstrip": false,
|
| 265 |
+
"normalized": false,
|
| 266 |
+
"rstrip": false,
|
| 267 |
+
"single_word": false,
|
| 268 |
+
"special": true
|
| 269 |
+
},
|
| 270 |
+
"151676": {
|
| 271 |
+
"content": "<box>",
|
| 272 |
+
"lstrip": false,
|
| 273 |
+
"normalized": false,
|
| 274 |
+
"rstrip": false,
|
| 275 |
+
"single_word": false,
|
| 276 |
+
"special": true
|
| 277 |
+
},
|
| 278 |
+
"151677": {
|
| 279 |
+
"content": "</box>",
|
| 280 |
+
"lstrip": false,
|
| 281 |
+
"normalized": false,
|
| 282 |
+
"rstrip": false,
|
| 283 |
+
"single_word": false,
|
| 284 |
+
"special": true
|
| 285 |
+
},
|
| 286 |
+
"151678": {
|
| 287 |
+
"content": "<vision_start>",
|
| 288 |
+
"lstrip": false,
|
| 289 |
+
"normalized": false,
|
| 290 |
+
"rstrip": false,
|
| 291 |
+
"single_word": false,
|
| 292 |
+
"special": true
|
| 293 |
+
},
|
| 294 |
+
"151679": {
|
| 295 |
+
"content": "<vision_end>",
|
| 296 |
+
"lstrip": false,
|
| 297 |
+
"normalized": false,
|
| 298 |
+
"rstrip": false,
|
| 299 |
+
"single_word": false,
|
| 300 |
+
"special": true
|
| 301 |
+
},
|
| 302 |
+
"151680": {
|
| 303 |
+
"content": "<|tac_start|>",
|
| 304 |
+
"lstrip": false,
|
| 305 |
+
"normalized": false,
|
| 306 |
+
"rstrip": false,
|
| 307 |
+
"single_word": false,
|
| 308 |
+
"special": true
|
| 309 |
+
},
|
| 310 |
+
"151681": {
|
| 311 |
+
"content": "<|tac_end|>",
|
| 312 |
+
"lstrip": false,
|
| 313 |
+
"normalized": false,
|
| 314 |
+
"rstrip": false,
|
| 315 |
+
"single_word": false,
|
| 316 |
+
"special": true
|
| 317 |
+
},
|
| 318 |
+
"151682": {
|
| 319 |
+
"content": "<|action_start|>",
|
| 320 |
+
"lstrip": false,
|
| 321 |
+
"normalized": false,
|
| 322 |
+
"rstrip": false,
|
| 323 |
+
"single_word": false,
|
| 324 |
+
"special": true
|
| 325 |
+
},
|
| 326 |
+
"151683": {
|
| 327 |
+
"content": "<|action_end|>",
|
| 328 |
+
"lstrip": false,
|
| 329 |
+
"normalized": false,
|
| 330 |
+
"rstrip": false,
|
| 331 |
+
"single_word": false,
|
| 332 |
+
"special": true
|
| 333 |
+
},
|
| 334 |
+
"151684": {
|
| 335 |
+
"content": "<|state_start|>",
|
| 336 |
+
"lstrip": false,
|
| 337 |
+
"normalized": false,
|
| 338 |
+
"rstrip": false,
|
| 339 |
+
"single_word": false,
|
| 340 |
+
"special": true
|
| 341 |
+
},
|
| 342 |
+
"151685": {
|
| 343 |
+
"content": "<|state_end|>",
|
| 344 |
+
"lstrip": false,
|
| 345 |
+
"normalized": false,
|
| 346 |
+
"rstrip": false,
|
| 347 |
+
"single_word": false,
|
| 348 |
+
"special": true
|
| 349 |
+
},
|
| 350 |
+
"151686": {
|
| 351 |
+
"content": "<PROP_CONTEXT>",
|
| 352 |
+
"lstrip": false,
|
| 353 |
+
"normalized": false,
|
| 354 |
+
"rstrip": false,
|
| 355 |
+
"single_word": false,
|
| 356 |
+
"special": true
|
| 357 |
+
},
|
| 358 |
+
"151687": {
|
| 359 |
+
"content": "<ACTION_TOKEN_0>",
|
| 360 |
+
"lstrip": false,
|
| 361 |
+
"normalized": false,
|
| 362 |
+
"rstrip": false,
|
| 363 |
+
"single_word": false,
|
| 364 |
+
"special": true
|
| 365 |
+
},
|
| 366 |
+
"151688": {
|
| 367 |
+
"content": "<ACTION_TOKEN_1>",
|
| 368 |
+
"lstrip": false,
|
| 369 |
+
"normalized": false,
|
| 370 |
+
"rstrip": false,
|
| 371 |
+
"single_word": false,
|
| 372 |
+
"special": true
|
| 373 |
+
},
|
| 374 |
+
"151689": {
|
| 375 |
+
"content": "<ACTION_TOKEN_2>",
|
| 376 |
+
"lstrip": false,
|
| 377 |
+
"normalized": false,
|
| 378 |
+
"rstrip": false,
|
| 379 |
+
"single_word": false,
|
| 380 |
+
"special": true
|
| 381 |
+
},
|
| 382 |
+
"151690": {
|
| 383 |
+
"content": "<ACTION_TOKEN_3>",
|
| 384 |
+
"lstrip": false,
|
| 385 |
+
"normalized": false,
|
| 386 |
+
"rstrip": false,
|
| 387 |
+
"single_word": false,
|
| 388 |
+
"special": true
|
| 389 |
+
},
|
| 390 |
+
"151691": {
|
| 391 |
+
"content": "<ACTION_TOKEN_4>",
|
| 392 |
+
"lstrip": false,
|
| 393 |
+
"normalized": false,
|
| 394 |
+
"rstrip": false,
|
| 395 |
+
"single_word": false,
|
| 396 |
+
"special": true
|
| 397 |
+
},
|
| 398 |
+
"151692": {
|
| 399 |
+
"content": "<ACTION_TOKEN_5>",
|
| 400 |
+
"lstrip": false,
|
| 401 |
+
"normalized": false,
|
| 402 |
+
"rstrip": false,
|
| 403 |
+
"single_word": false,
|
| 404 |
+
"special": true
|
| 405 |
+
},
|
| 406 |
+
"151693": {
|
| 407 |
+
"content": "<ACTION_TOKEN_6>",
|
| 408 |
+
"lstrip": false,
|
| 409 |
+
"normalized": false,
|
| 410 |
+
"rstrip": false,
|
| 411 |
+
"single_word": false,
|
| 412 |
+
"special": true
|
| 413 |
+
},
|
| 414 |
+
"151694": {
|
| 415 |
+
"content": "<ACTION_TOKEN_7>",
|
| 416 |
+
"lstrip": false,
|
| 417 |
+
"normalized": false,
|
| 418 |
+
"rstrip": false,
|
| 419 |
+
"single_word": false,
|
| 420 |
+
"special": true
|
| 421 |
+
}
|
| 422 |
+
},
|
| 423 |
+
"additional_special_tokens": [
|
| 424 |
+
"<|im_start|>",
|
| 425 |
+
"<|im_end|>",
|
| 426 |
+
"<|object_ref_start|>",
|
| 427 |
+
"<|object_ref_end|>",
|
| 428 |
+
"<|box_start|>",
|
| 429 |
+
"<|box_end|>",
|
| 430 |
+
"<|quad_start|>",
|
| 431 |
+
"<|quad_end|>",
|
| 432 |
+
"<|vision_start|>",
|
| 433 |
+
"<|vision_end|>",
|
| 434 |
+
"<|vision_pad|>",
|
| 435 |
+
"<|image_pad|>",
|
| 436 |
+
"<|video_pad|>",
|
| 437 |
+
"<img>",
|
| 438 |
+
"</img>",
|
| 439 |
+
"<IMG_CONTEXT>",
|
| 440 |
+
"<quad>",
|
| 441 |
+
"</quad>",
|
| 442 |
+
"<ref>",
|
| 443 |
+
"</ref>",
|
| 444 |
+
"<box>",
|
| 445 |
+
"</box>"
|
| 446 |
+
],
|
| 447 |
+
"bos_token": null,
|
| 448 |
+
"clean_up_tokenization_spaces": false,
|
| 449 |
+
"eos_token": "<|im_end|>",
|
| 450 |
+
"errors": "replace",
|
| 451 |
+
"extra_special_tokens": {},
|
| 452 |
+
"model_max_length": 14588,
|
| 453 |
+
"pad_token": "<|endoftext|>",
|
| 454 |
+
"processor_class": "InternVLProcessor",
|
| 455 |
+
"split_special_tokens": false,
|
| 456 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 457 |
+
"unk_token": null
|
| 458 |
+
}
|
libero/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pretrained/added_tokens.json
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</box>": 151677,
|
| 3 |
+
"</img>": 151670,
|
| 4 |
+
"</quad>": 151673,
|
| 5 |
+
"</ref>": 151675,
|
| 6 |
+
"</think>": 151668,
|
| 7 |
+
"</tool_call>": 151658,
|
| 8 |
+
"</tool_response>": 151666,
|
| 9 |
+
"<ACTION_TOKEN_0>": 151687,
|
| 10 |
+
"<ACTION_TOKEN_10>": 151697,
|
| 11 |
+
"<ACTION_TOKEN_11>": 151698,
|
| 12 |
+
"<ACTION_TOKEN_12>": 151699,
|
| 13 |
+
"<ACTION_TOKEN_13>": 151700,
|
| 14 |
+
"<ACTION_TOKEN_14>": 151701,
|
| 15 |
+
"<ACTION_TOKEN_15>": 151702,
|
| 16 |
+
"<ACTION_TOKEN_16>": 151703,
|
| 17 |
+
"<ACTION_TOKEN_17>": 151704,
|
| 18 |
+
"<ACTION_TOKEN_18>": 151705,
|
| 19 |
+
"<ACTION_TOKEN_19>": 151706,
|
| 20 |
+
"<ACTION_TOKEN_1>": 151688,
|
| 21 |
+
"<ACTION_TOKEN_20>": 151707,
|
| 22 |
+
"<ACTION_TOKEN_21>": 151708,
|
| 23 |
+
"<ACTION_TOKEN_22>": 151709,
|
| 24 |
+
"<ACTION_TOKEN_23>": 151710,
|
| 25 |
+
"<ACTION_TOKEN_24>": 151711,
|
| 26 |
+
"<ACTION_TOKEN_25>": 151712,
|
| 27 |
+
"<ACTION_TOKEN_26>": 151713,
|
| 28 |
+
"<ACTION_TOKEN_27>": 151714,
|
| 29 |
+
"<ACTION_TOKEN_28>": 151715,
|
| 30 |
+
"<ACTION_TOKEN_29>": 151716,
|
| 31 |
+
"<ACTION_TOKEN_2>": 151689,
|
| 32 |
+
"<ACTION_TOKEN_30>": 151717,
|
| 33 |
+
"<ACTION_TOKEN_31>": 151718,
|
| 34 |
+
"<ACTION_TOKEN_3>": 151690,
|
| 35 |
+
"<ACTION_TOKEN_4>": 151691,
|
| 36 |
+
"<ACTION_TOKEN_5>": 151692,
|
| 37 |
+
"<ACTION_TOKEN_6>": 151693,
|
| 38 |
+
"<ACTION_TOKEN_7>": 151694,
|
| 39 |
+
"<ACTION_TOKEN_8>": 151695,
|
| 40 |
+
"<ACTION_TOKEN_9>": 151696,
|
| 41 |
+
"<IMG_CONTEXT>": 151671,
|
| 42 |
+
"<PROP_CONTEXT>": 151686,
|
| 43 |
+
"<box>": 151676,
|
| 44 |
+
"<img>": 151669,
|
| 45 |
+
"<quad>": 151672,
|
| 46 |
+
"<ref>": 151674,
|
| 47 |
+
"<think>": 151667,
|
| 48 |
+
"<tool_call>": 151657,
|
| 49 |
+
"<tool_response>": 151665,
|
| 50 |
+
"<vision_end>": 151679,
|
| 51 |
+
"<vision_start>": 151678,
|
| 52 |
+
"<|action_end|>": 151683,
|
| 53 |
+
"<|action_start|>": 151682,
|
| 54 |
+
"<|box_end|>": 151649,
|
| 55 |
+
"<|box_start|>": 151648,
|
| 56 |
+
"<|endoftext|>": 151643,
|
| 57 |
+
"<|file_sep|>": 151664,
|
| 58 |
+
"<|fim_middle|>": 151660,
|
| 59 |
+
"<|fim_pad|>": 151662,
|
| 60 |
+
"<|fim_prefix|>": 151659,
|
| 61 |
+
"<|fim_suffix|>": 151661,
|
| 62 |
+
"<|im_end|>": 151645,
|
| 63 |
+
"<|im_start|>": 151644,
|
| 64 |
+
"<|image_pad|>": 151655,
|
| 65 |
+
"<|object_ref_end|>": 151647,
|
| 66 |
+
"<|object_ref_start|>": 151646,
|
| 67 |
+
"<|quad_end|>": 151651,
|
| 68 |
+
"<|quad_start|>": 151650,
|
| 69 |
+
"<|repo_name|>": 151663,
|
| 70 |
+
"<|state_end|>": 151685,
|
| 71 |
+
"<|state_start|>": 151684,
|
| 72 |
+
"<|tac_end|>": 151681,
|
| 73 |
+
"<|tac_start|>": 151680,
|
| 74 |
+
"<|video_pad|>": 151656,
|
| 75 |
+
"<|vision_end|>": 151653,
|
| 76 |
+
"<|vision_pad|>": 151654,
|
| 77 |
+
"<|vision_start|>": 151652
|
| 78 |
+
}
|
pretrained/chat_template.jinja
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{{'<|im_start|>' + message['role'] + '
|
| 2 |
+
'}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<image>
|
| 3 |
+
' }}{% elif content['type'] == 'video' %}{{ '<video>
|
| 4 |
+
' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>
|
| 5 |
+
'}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
|
| 6 |
+
' }}{% endif %}
|
pretrained/config.json
ADDED
|
@@ -0,0 +1,366 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"return_dict": true,
|
| 3 |
+
"output_hidden_states": false,
|
| 4 |
+
"torchscript": false,
|
| 5 |
+
"dtype": null,
|
| 6 |
+
"pruned_heads": {},
|
| 7 |
+
"tie_word_embeddings": true,
|
| 8 |
+
"chunk_size_feed_forward": 0,
|
| 9 |
+
"is_encoder_decoder": false,
|
| 10 |
+
"is_decoder": false,
|
| 11 |
+
"cross_attention_hidden_size": null,
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"tie_encoder_decoder": false,
|
| 14 |
+
"architectures": null,
|
| 15 |
+
"finetuning_task": null,
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "LABEL_0",
|
| 18 |
+
"1": "LABEL_1"
|
| 19 |
+
},
|
| 20 |
+
"label2id": {
|
| 21 |
+
"LABEL_0": 0,
|
| 22 |
+
"LABEL_1": 1
|
| 23 |
+
},
|
| 24 |
+
"task_specific_params": null,
|
| 25 |
+
"problem_type": null,
|
| 26 |
+
"tokenizer_class": null,
|
| 27 |
+
"prefix": null,
|
| 28 |
+
"bos_token_id": null,
|
| 29 |
+
"pad_token_id": null,
|
| 30 |
+
"eos_token_id": null,
|
| 31 |
+
"sep_token_id": null,
|
| 32 |
+
"decoder_start_token_id": null,
|
| 33 |
+
"max_length": 20,
|
| 34 |
+
"min_length": 0,
|
| 35 |
+
"do_sample": false,
|
| 36 |
+
"early_stopping": false,
|
| 37 |
+
"num_beams": 1,
|
| 38 |
+
"temperature": 1.0,
|
| 39 |
+
"top_k": 50,
|
| 40 |
+
"top_p": 1.0,
|
| 41 |
+
"typical_p": 1.0,
|
| 42 |
+
"repetition_penalty": 1.0,
|
| 43 |
+
"length_penalty": 1.0,
|
| 44 |
+
"no_repeat_ngram_size": 0,
|
| 45 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 46 |
+
"bad_words_ids": null,
|
| 47 |
+
"num_return_sequences": 1,
|
| 48 |
+
"output_scores": false,
|
| 49 |
+
"return_dict_in_generate": false,
|
| 50 |
+
"forced_bos_token_id": null,
|
| 51 |
+
"forced_eos_token_id": null,
|
| 52 |
+
"remove_invalid_values": false,
|
| 53 |
+
"exponential_decay_length_penalty": null,
|
| 54 |
+
"suppress_tokens": null,
|
| 55 |
+
"begin_suppress_tokens": null,
|
| 56 |
+
"num_beam_groups": 1,
|
| 57 |
+
"diversity_penalty": 0.0,
|
| 58 |
+
"_name_or_path": "",
|
| 59 |
+
"transformers_version": "4.57.1",
|
| 60 |
+
"use_mpg": true,
|
| 61 |
+
"mpg_num_projections": 32,
|
| 62 |
+
"mpg_lambda": 0.0,
|
| 63 |
+
"mpg_use_stop_gradient": true,
|
| 64 |
+
"mpg_refinement_iters": 1,
|
| 65 |
+
"mpg_gate_temperature": 1.0,
|
| 66 |
+
"use_training_time_rtc": false,
|
| 67 |
+
"simulated_delay": 0,
|
| 68 |
+
"rtc_delay_exp_weight": true,
|
| 69 |
+
"use_inference_prefix_overwrite": true,
|
| 70 |
+
"tf_legacy_loss": false,
|
| 71 |
+
"use_bfloat16": false,
|
| 72 |
+
"llm_config": {
|
| 73 |
+
"vocab_size": 151719,
|
| 74 |
+
"max_position_embeddings": 40960,
|
| 75 |
+
"hidden_size": 2048,
|
| 76 |
+
"intermediate_size": 6144,
|
| 77 |
+
"num_hidden_layers": 28,
|
| 78 |
+
"num_attention_heads": 16,
|
| 79 |
+
"use_sliding_window": false,
|
| 80 |
+
"sliding_window": null,
|
| 81 |
+
"max_window_layers": 28,
|
| 82 |
+
"num_key_value_heads": 8,
|
| 83 |
+
"hidden_act": "silu",
|
| 84 |
+
"initializer_range": 0.02,
|
| 85 |
+
"rms_norm_eps": 1e-06,
|
| 86 |
+
"use_cache": false,
|
| 87 |
+
"rope_theta": 1000000,
|
| 88 |
+
"rope_scaling": null,
|
| 89 |
+
"attention_bias": false,
|
| 90 |
+
"attention_dropout": 0.0,
|
| 91 |
+
"is_causal": true,
|
| 92 |
+
"return_dict": true,
|
| 93 |
+
"output_hidden_states": false,
|
| 94 |
+
"torchscript": false,
|
| 95 |
+
"dtype": "bfloat16",
|
| 96 |
+
"pruned_heads": {},
|
| 97 |
+
"tie_word_embeddings": false,
|
| 98 |
+
"chunk_size_feed_forward": 0,
|
| 99 |
+
"is_encoder_decoder": false,
|
| 100 |
+
"is_decoder": false,
|
| 101 |
+
"cross_attention_hidden_size": null,
|
| 102 |
+
"add_cross_attention": false,
|
| 103 |
+
"tie_encoder_decoder": false,
|
| 104 |
+
"architectures": [
|
| 105 |
+
"Qwen3ForCausalLM"
|
| 106 |
+
],
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"id2label": {
|
| 109 |
+
"0": "LABEL_0",
|
| 110 |
+
"1": "LABEL_1"
|
| 111 |
+
},
|
| 112 |
+
"label2id": {
|
| 113 |
+
"LABEL_0": 0,
|
| 114 |
+
"LABEL_1": 1
|
| 115 |
+
},
|
| 116 |
+
"task_specific_params": null,
|
| 117 |
+
"problem_type": null,
|
| 118 |
+
"tokenizer_class": null,
|
| 119 |
+
"prefix": null,
|
| 120 |
+
"bos_token_id": 151643,
|
| 121 |
+
"pad_token_id": null,
|
| 122 |
+
"eos_token_id": 151645,
|
| 123 |
+
"sep_token_id": null,
|
| 124 |
+
"decoder_start_token_id": null,
|
| 125 |
+
"max_length": 20,
|
| 126 |
+
"min_length": 0,
|
| 127 |
+
"do_sample": false,
|
| 128 |
+
"early_stopping": false,
|
| 129 |
+
"num_beams": 1,
|
| 130 |
+
"temperature": 1.0,
|
| 131 |
+
"top_k": 50,
|
| 132 |
+
"top_p": 1.0,
|
| 133 |
+
"typical_p": 1.0,
|
| 134 |
+
"repetition_penalty": 1.0,
|
| 135 |
+
"length_penalty": 1.0,
|
| 136 |
+
"no_repeat_ngram_size": 0,
|
| 137 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 138 |
+
"bad_words_ids": null,
|
| 139 |
+
"num_return_sequences": 1,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"return_dict_in_generate": false,
|
| 142 |
+
"forced_bos_token_id": null,
|
| 143 |
+
"forced_eos_token_id": null,
|
| 144 |
+
"remove_invalid_values": false,
|
| 145 |
+
"exponential_decay_length_penalty": null,
|
| 146 |
+
"suppress_tokens": null,
|
| 147 |
+
"begin_suppress_tokens": null,
|
| 148 |
+
"num_beam_groups": 1,
|
| 149 |
+
"diversity_penalty": 0.0,
|
| 150 |
+
"_name_or_path": "/root/codespace/checkpoints/Qwen3-1.7B",
|
| 151 |
+
"debug": false,
|
| 152 |
+
"ep_size": 1,
|
| 153 |
+
"head_dim": 128,
|
| 154 |
+
"micro_forward": false,
|
| 155 |
+
"model_type": "qwen3",
|
| 156 |
+
"skip_checkpoint": false,
|
| 157 |
+
"use_deepep": false,
|
| 158 |
+
"tf_legacy_loss": false,
|
| 159 |
+
"use_bfloat16": false,
|
| 160 |
+
"qk_norm": true,
|
| 161 |
+
"layer_module": "Qwen3MoTDecoderLayer",
|
| 162 |
+
"use_mot": true,
|
| 163 |
+
"expert_config": {
|
| 164 |
+
"vocab_size": 151936,
|
| 165 |
+
"max_position_embeddings": 40960,
|
| 166 |
+
"hidden_size": 1024,
|
| 167 |
+
"intermediate_size": 3072,
|
| 168 |
+
"num_hidden_layers": 28,
|
| 169 |
+
"num_attention_heads": 16,
|
| 170 |
+
"use_sliding_window": false,
|
| 171 |
+
"sliding_window": null,
|
| 172 |
+
"max_window_layers": 28,
|
| 173 |
+
"num_key_value_heads": 8,
|
| 174 |
+
"hidden_act": "silu",
|
| 175 |
+
"initializer_range": 0.02,
|
| 176 |
+
"rms_norm_eps": 1e-06,
|
| 177 |
+
"use_cache": true,
|
| 178 |
+
"rope_theta": 1000000,
|
| 179 |
+
"rope_scaling": null,
|
| 180 |
+
"attention_bias": false,
|
| 181 |
+
"attention_dropout": 0.0,
|
| 182 |
+
"is_causal": true,
|
| 183 |
+
"return_dict": true,
|
| 184 |
+
"output_hidden_states": false,
|
| 185 |
+
"torchscript": false,
|
| 186 |
+
"dtype": "bfloat16",
|
| 187 |
+
"pruned_heads": {},
|
| 188 |
+
"tie_word_embeddings": true,
|
| 189 |
+
"chunk_size_feed_forward": 0,
|
| 190 |
+
"is_encoder_decoder": false,
|
| 191 |
+
"is_decoder": false,
|
| 192 |
+
"cross_attention_hidden_size": null,
|
| 193 |
+
"add_cross_attention": false,
|
| 194 |
+
"tie_encoder_decoder": false,
|
| 195 |
+
"architectures": [
|
| 196 |
+
"Qwen3ForCausalLM"
|
| 197 |
+
],
|
| 198 |
+
"finetuning_task": null,
|
| 199 |
+
"id2label": {
|
| 200 |
+
"0": "LABEL_0",
|
| 201 |
+
"1": "LABEL_1"
|
| 202 |
+
},
|
| 203 |
+
"label2id": {
|
| 204 |
+
"LABEL_0": 0,
|
| 205 |
+
"LABEL_1": 1
|
| 206 |
+
},
|
| 207 |
+
"task_specific_params": null,
|
| 208 |
+
"problem_type": null,
|
| 209 |
+
"tokenizer_class": null,
|
| 210 |
+
"prefix": null,
|
| 211 |
+
"bos_token_id": 151643,
|
| 212 |
+
"pad_token_id": null,
|
| 213 |
+
"eos_token_id": 151645,
|
| 214 |
+
"sep_token_id": null,
|
| 215 |
+
"decoder_start_token_id": null,
|
| 216 |
+
"max_length": 20,
|
| 217 |
+
"min_length": 0,
|
| 218 |
+
"do_sample": false,
|
| 219 |
+
"early_stopping": false,
|
| 220 |
+
"num_beams": 1,
|
| 221 |
+
"temperature": 1.0,
|
| 222 |
+
"top_k": 50,
|
| 223 |
+
"top_p": 1.0,
|
| 224 |
+
"typical_p": 1.0,
|
| 225 |
+
"repetition_penalty": 1.0,
|
| 226 |
+
"length_penalty": 1.0,
|
| 227 |
+
"no_repeat_ngram_size": 0,
|
| 228 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 229 |
+
"bad_words_ids": null,
|
| 230 |
+
"num_return_sequences": 1,
|
| 231 |
+
"output_scores": false,
|
| 232 |
+
"return_dict_in_generate": false,
|
| 233 |
+
"forced_bos_token_id": null,
|
| 234 |
+
"forced_eos_token_id": null,
|
| 235 |
+
"remove_invalid_values": false,
|
| 236 |
+
"exponential_decay_length_penalty": null,
|
| 237 |
+
"suppress_tokens": null,
|
| 238 |
+
"begin_suppress_tokens": null,
|
| 239 |
+
"num_beam_groups": 1,
|
| 240 |
+
"diversity_penalty": 0.0,
|
| 241 |
+
"_name_or_path": "",
|
| 242 |
+
"head_dim": 128,
|
| 243 |
+
"model_type": "qwen3",
|
| 244 |
+
"tf_legacy_loss": false,
|
| 245 |
+
"use_bfloat16": false,
|
| 246 |
+
"qk_norm": true,
|
| 247 |
+
"layer_module": "Qwen3DecoderLayer",
|
| 248 |
+
"output_attentions": false
|
| 249 |
+
},
|
| 250 |
+
"attn_implementation": "flash_attention_2",
|
| 251 |
+
"output_attentions": false
|
| 252 |
+
},
|
| 253 |
+
"vit_config": {
|
| 254 |
+
"return_dict": true,
|
| 255 |
+
"output_hidden_states": false,
|
| 256 |
+
"torchscript": false,
|
| 257 |
+
"dtype": "bfloat16",
|
| 258 |
+
"pruned_heads": {},
|
| 259 |
+
"tie_word_embeddings": true,
|
| 260 |
+
"chunk_size_feed_forward": 0,
|
| 261 |
+
"is_encoder_decoder": false,
|
| 262 |
+
"is_decoder": false,
|
| 263 |
+
"cross_attention_hidden_size": null,
|
| 264 |
+
"add_cross_attention": false,
|
| 265 |
+
"tie_encoder_decoder": false,
|
| 266 |
+
"architectures": [
|
| 267 |
+
"InternVisionModel"
|
| 268 |
+
],
|
| 269 |
+
"finetuning_task": null,
|
| 270 |
+
"id2label": {
|
| 271 |
+
"0": "LABEL_0",
|
| 272 |
+
"1": "LABEL_1"
|
| 273 |
+
},
|
| 274 |
+
"label2id": {
|
| 275 |
+
"LABEL_0": 0,
|
| 276 |
+
"LABEL_1": 1
|
| 277 |
+
},
|
| 278 |
+
"task_specific_params": null,
|
| 279 |
+
"problem_type": null,
|
| 280 |
+
"tokenizer_class": null,
|
| 281 |
+
"prefix": null,
|
| 282 |
+
"bos_token_id": null,
|
| 283 |
+
"pad_token_id": null,
|
| 284 |
+
"eos_token_id": null,
|
| 285 |
+
"sep_token_id": null,
|
| 286 |
+
"decoder_start_token_id": null,
|
| 287 |
+
"max_length": 20,
|
| 288 |
+
"min_length": 0,
|
| 289 |
+
"do_sample": false,
|
| 290 |
+
"early_stopping": false,
|
| 291 |
+
"num_beams": 1,
|
| 292 |
+
"temperature": 1.0,
|
| 293 |
+
"top_k": 50,
|
| 294 |
+
"top_p": 1.0,
|
| 295 |
+
"typical_p": 1.0,
|
| 296 |
+
"repetition_penalty": 1.0,
|
| 297 |
+
"length_penalty": 1.0,
|
| 298 |
+
"no_repeat_ngram_size": 0,
|
| 299 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 300 |
+
"bad_words_ids": null,
|
| 301 |
+
"num_return_sequences": 1,
|
| 302 |
+
"output_scores": false,
|
| 303 |
+
"return_dict_in_generate": false,
|
| 304 |
+
"forced_bos_token_id": null,
|
| 305 |
+
"forced_eos_token_id": null,
|
| 306 |
+
"remove_invalid_values": false,
|
| 307 |
+
"exponential_decay_length_penalty": null,
|
| 308 |
+
"suppress_tokens": null,
|
| 309 |
+
"begin_suppress_tokens": null,
|
| 310 |
+
"num_beam_groups": 1,
|
| 311 |
+
"diversity_penalty": 0.0,
|
| 312 |
+
"_name_or_path": "",
|
| 313 |
+
"auto_map": {
|
| 314 |
+
"AutoConfig": "configuration_intern_vit.InternVisionConfig",
|
| 315 |
+
"AutoModel": "modeling_intern_vit.InternVisionModel"
|
| 316 |
+
},
|
| 317 |
+
"model_type": "intern_vit_6b",
|
| 318 |
+
"use_fa3": false,
|
| 319 |
+
"tf_legacy_loss": false,
|
| 320 |
+
"use_bfloat16": false,
|
| 321 |
+
"hidden_size": 1024,
|
| 322 |
+
"intermediate_size": 4096,
|
| 323 |
+
"dropout": 0.0,
|
| 324 |
+
"drop_path_rate": 0.0,
|
| 325 |
+
"num_hidden_layers": 24,
|
| 326 |
+
"num_attention_heads": 16,
|
| 327 |
+
"num_channels": 3,
|
| 328 |
+
"patch_size": 14,
|
| 329 |
+
"image_size": 448,
|
| 330 |
+
"initializer_range": 0.02,
|
| 331 |
+
"initializer_factor": 1.0,
|
| 332 |
+
"attention_dropout": 0.0,
|
| 333 |
+
"layer_norm_eps": 1e-06,
|
| 334 |
+
"hidden_act": "gelu",
|
| 335 |
+
"norm_type": "layer_norm",
|
| 336 |
+
"qkv_bias": true,
|
| 337 |
+
"qk_normalization": false,
|
| 338 |
+
"use_flash_attn": true,
|
| 339 |
+
"select_layer": -1,
|
| 340 |
+
"downsample_ratio": 0.5,
|
| 341 |
+
"output_attentions": false
|
| 342 |
+
},
|
| 343 |
+
"connector_arch": "internvl_connector",
|
| 344 |
+
"template": "internlm2-chat",
|
| 345 |
+
"select_layer": -1,
|
| 346 |
+
"force_image_size": 448,
|
| 347 |
+
"downsample_ratio": 0.5,
|
| 348 |
+
"action_chunk_length": 32,
|
| 349 |
+
"loss_func": "l1",
|
| 350 |
+
"gen_action_type": "prop_hidden",
|
| 351 |
+
"layer_select_for_action": -1,
|
| 352 |
+
"action_token_num": 32,
|
| 353 |
+
"learnable_action_query": false,
|
| 354 |
+
"prompt_template": "long",
|
| 355 |
+
"use_expert": true,
|
| 356 |
+
"use_flow_matching": true,
|
| 357 |
+
"attn_mode": "causal",
|
| 358 |
+
"max_num_embodiments": 32,
|
| 359 |
+
"noise_beta_alpha": 1.5,
|
| 360 |
+
"noise_beta_beta": 1.0,
|
| 361 |
+
"num_timestep_buckets": 1000,
|
| 362 |
+
"noise_s": 0.999,
|
| 363 |
+
"num_inference_timesteps": 4,
|
| 364 |
+
"model_type": "beingh",
|
| 365 |
+
"output_attentions": false
|
| 366 |
+
}
|
pretrained/human_tactile_pretrain_metadata.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pretrained/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pretrained/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ac53ab541ac9b8e721a58b7652bc52c5a5aba740c8c9acd4c069c9864f96b5f
|
| 3 |
+
size 11288853888
|
pretrained/special_tokens_map.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>",
|
| 16 |
+
"<img>",
|
| 17 |
+
"</img>",
|
| 18 |
+
"<IMG_CONTEXT>",
|
| 19 |
+
"<quad>",
|
| 20 |
+
"</quad>",
|
| 21 |
+
"<ref>",
|
| 22 |
+
"</ref>",
|
| 23 |
+
"<box>",
|
| 24 |
+
"</box>"
|
| 25 |
+
],
|
| 26 |
+
"eos_token": {
|
| 27 |
+
"content": "<|im_end|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"pad_token": {
|
| 34 |
+
"content": "<|endoftext|>",
|
| 35 |
+
"lstrip": false,
|
| 36 |
+
"normalized": false,
|
| 37 |
+
"rstrip": false,
|
| 38 |
+
"single_word": false
|
| 39 |
+
}
|
| 40 |
+
}
|
pretrained/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fc7ce604eec3ffd2670c269c1ceddf1a7a898d2b6981d3832658c3f7704e186
|
| 3 |
+
size 11432213
|
pretrained/tokenizer_config.json
ADDED
|
@@ -0,0 +1,650 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"151643": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"151644": {
|
| 15 |
+
"content": "<|im_start|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"151645": {
|
| 23 |
+
"content": "<|im_end|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"151646": {
|
| 31 |
+
"content": "<|object_ref_start|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"151647": {
|
| 39 |
+
"content": "<|object_ref_end|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"151648": {
|
| 47 |
+
"content": "<|box_start|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"151649": {
|
| 55 |
+
"content": "<|box_end|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"151650": {
|
| 63 |
+
"content": "<|quad_start|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"151651": {
|
| 71 |
+
"content": "<|quad_end|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"151652": {
|
| 79 |
+
"content": "<|vision_start|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"151653": {
|
| 87 |
+
"content": "<|vision_end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"151654": {
|
| 95 |
+
"content": "<|vision_pad|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"151655": {
|
| 103 |
+
"content": "<|image_pad|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"151656": {
|
| 111 |
+
"content": "<|video_pad|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"151657": {
|
| 119 |
+
"content": "<tool_call>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"151658": {
|
| 127 |
+
"content": "</tool_call>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"151659": {
|
| 135 |
+
"content": "<|fim_prefix|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"151660": {
|
| 143 |
+
"content": "<|fim_middle|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"151661": {
|
| 151 |
+
"content": "<|fim_suffix|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"151662": {
|
| 159 |
+
"content": "<|fim_pad|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"151663": {
|
| 167 |
+
"content": "<|repo_name|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"151664": {
|
| 175 |
+
"content": "<|file_sep|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
},
|
| 182 |
+
"151665": {
|
| 183 |
+
"content": "<tool_response>",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": false,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": false
|
| 189 |
+
},
|
| 190 |
+
"151666": {
|
| 191 |
+
"content": "</tool_response>",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": false,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": false
|
| 197 |
+
},
|
| 198 |
+
"151667": {
|
| 199 |
+
"content": "<think>",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": false
|
| 205 |
+
},
|
| 206 |
+
"151668": {
|
| 207 |
+
"content": "</think>",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": false,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false,
|
| 212 |
+
"special": false
|
| 213 |
+
},
|
| 214 |
+
"151669": {
|
| 215 |
+
"content": "<img>",
|
| 216 |
+
"lstrip": false,
|
| 217 |
+
"normalized": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"single_word": false,
|
| 220 |
+
"special": true
|
| 221 |
+
},
|
| 222 |
+
"151670": {
|
| 223 |
+
"content": "</img>",
|
| 224 |
+
"lstrip": false,
|
| 225 |
+
"normalized": false,
|
| 226 |
+
"rstrip": false,
|
| 227 |
+
"single_word": false,
|
| 228 |
+
"special": true
|
| 229 |
+
},
|
| 230 |
+
"151671": {
|
| 231 |
+
"content": "<IMG_CONTEXT>",
|
| 232 |
+
"lstrip": false,
|
| 233 |
+
"normalized": false,
|
| 234 |
+
"rstrip": false,
|
| 235 |
+
"single_word": false,
|
| 236 |
+
"special": true
|
| 237 |
+
},
|
| 238 |
+
"151672": {
|
| 239 |
+
"content": "<quad>",
|
| 240 |
+
"lstrip": false,
|
| 241 |
+
"normalized": false,
|
| 242 |
+
"rstrip": false,
|
| 243 |
+
"single_word": false,
|
| 244 |
+
"special": true
|
| 245 |
+
},
|
| 246 |
+
"151673": {
|
| 247 |
+
"content": "</quad>",
|
| 248 |
+
"lstrip": false,
|
| 249 |
+
"normalized": false,
|
| 250 |
+
"rstrip": false,
|
| 251 |
+
"single_word": false,
|
| 252 |
+
"special": true
|
| 253 |
+
},
|
| 254 |
+
"151674": {
|
| 255 |
+
"content": "<ref>",
|
| 256 |
+
"lstrip": false,
|
| 257 |
+
"normalized": false,
|
| 258 |
+
"rstrip": false,
|
| 259 |
+
"single_word": false,
|
| 260 |
+
"special": true
|
| 261 |
+
},
|
| 262 |
+
"151675": {
|
| 263 |
+
"content": "</ref>",
|
| 264 |
+
"lstrip": false,
|
| 265 |
+
"normalized": false,
|
| 266 |
+
"rstrip": false,
|
| 267 |
+
"single_word": false,
|
| 268 |
+
"special": true
|
| 269 |
+
},
|
| 270 |
+
"151676": {
|
| 271 |
+
"content": "<box>",
|
| 272 |
+
"lstrip": false,
|
| 273 |
+
"normalized": false,
|
| 274 |
+
"rstrip": false,
|
| 275 |
+
"single_word": false,
|
| 276 |
+
"special": true
|
| 277 |
+
},
|
| 278 |
+
"151677": {
|
| 279 |
+
"content": "</box>",
|
| 280 |
+
"lstrip": false,
|
| 281 |
+
"normalized": false,
|
| 282 |
+
"rstrip": false,
|
| 283 |
+
"single_word": false,
|
| 284 |
+
"special": true
|
| 285 |
+
},
|
| 286 |
+
"151678": {
|
| 287 |
+
"content": "<vision_start>",
|
| 288 |
+
"lstrip": false,
|
| 289 |
+
"normalized": false,
|
| 290 |
+
"rstrip": false,
|
| 291 |
+
"single_word": false,
|
| 292 |
+
"special": true
|
| 293 |
+
},
|
| 294 |
+
"151679": {
|
| 295 |
+
"content": "<vision_end>",
|
| 296 |
+
"lstrip": false,
|
| 297 |
+
"normalized": false,
|
| 298 |
+
"rstrip": false,
|
| 299 |
+
"single_word": false,
|
| 300 |
+
"special": true
|
| 301 |
+
},
|
| 302 |
+
"151680": {
|
| 303 |
+
"content": "<|tac_start|>",
|
| 304 |
+
"lstrip": false,
|
| 305 |
+
"normalized": false,
|
| 306 |
+
"rstrip": false,
|
| 307 |
+
"single_word": false,
|
| 308 |
+
"special": true
|
| 309 |
+
},
|
| 310 |
+
"151681": {
|
| 311 |
+
"content": "<|tac_end|>",
|
| 312 |
+
"lstrip": false,
|
| 313 |
+
"normalized": false,
|
| 314 |
+
"rstrip": false,
|
| 315 |
+
"single_word": false,
|
| 316 |
+
"special": true
|
| 317 |
+
},
|
| 318 |
+
"151682": {
|
| 319 |
+
"content": "<|action_start|>",
|
| 320 |
+
"lstrip": false,
|
| 321 |
+
"normalized": false,
|
| 322 |
+
"rstrip": false,
|
| 323 |
+
"single_word": false,
|
| 324 |
+
"special": true
|
| 325 |
+
},
|
| 326 |
+
"151683": {
|
| 327 |
+
"content": "<|action_end|>",
|
| 328 |
+
"lstrip": false,
|
| 329 |
+
"normalized": false,
|
| 330 |
+
"rstrip": false,
|
| 331 |
+
"single_word": false,
|
| 332 |
+
"special": true
|
| 333 |
+
},
|
| 334 |
+
"151684": {
|
| 335 |
+
"content": "<|state_start|>",
|
| 336 |
+
"lstrip": false,
|
| 337 |
+
"normalized": false,
|
| 338 |
+
"rstrip": false,
|
| 339 |
+
"single_word": false,
|
| 340 |
+
"special": true
|
| 341 |
+
},
|
| 342 |
+
"151685": {
|
| 343 |
+
"content": "<|state_end|>",
|
| 344 |
+
"lstrip": false,
|
| 345 |
+
"normalized": false,
|
| 346 |
+
"rstrip": false,
|
| 347 |
+
"single_word": false,
|
| 348 |
+
"special": true
|
| 349 |
+
},
|
| 350 |
+
"151686": {
|
| 351 |
+
"content": "<PROP_CONTEXT>",
|
| 352 |
+
"lstrip": false,
|
| 353 |
+
"normalized": false,
|
| 354 |
+
"rstrip": false,
|
| 355 |
+
"single_word": false,
|
| 356 |
+
"special": true
|
| 357 |
+
},
|
| 358 |
+
"151687": {
|
| 359 |
+
"content": "<ACTION_TOKEN_0>",
|
| 360 |
+
"lstrip": false,
|
| 361 |
+
"normalized": false,
|
| 362 |
+
"rstrip": false,
|
| 363 |
+
"single_word": false,
|
| 364 |
+
"special": true
|
| 365 |
+
},
|
| 366 |
+
"151688": {
|
| 367 |
+
"content": "<ACTION_TOKEN_1>",
|
| 368 |
+
"lstrip": false,
|
| 369 |
+
"normalized": false,
|
| 370 |
+
"rstrip": false,
|
| 371 |
+
"single_word": false,
|
| 372 |
+
"special": true
|
| 373 |
+
},
|
| 374 |
+
"151689": {
|
| 375 |
+
"content": "<ACTION_TOKEN_2>",
|
| 376 |
+
"lstrip": false,
|
| 377 |
+
"normalized": false,
|
| 378 |
+
"rstrip": false,
|
| 379 |
+
"single_word": false,
|
| 380 |
+
"special": true
|
| 381 |
+
},
|
| 382 |
+
"151690": {
|
| 383 |
+
"content": "<ACTION_TOKEN_3>",
|
| 384 |
+
"lstrip": false,
|
| 385 |
+
"normalized": false,
|
| 386 |
+
"rstrip": false,
|
| 387 |
+
"single_word": false,
|
| 388 |
+
"special": true
|
| 389 |
+
},
|
| 390 |
+
"151691": {
|
| 391 |
+
"content": "<ACTION_TOKEN_4>",
|
| 392 |
+
"lstrip": false,
|
| 393 |
+
"normalized": false,
|
| 394 |
+
"rstrip": false,
|
| 395 |
+
"single_word": false,
|
| 396 |
+
"special": true
|
| 397 |
+
},
|
| 398 |
+
"151692": {
|
| 399 |
+
"content": "<ACTION_TOKEN_5>",
|
| 400 |
+
"lstrip": false,
|
| 401 |
+
"normalized": false,
|
| 402 |
+
"rstrip": false,
|
| 403 |
+
"single_word": false,
|
| 404 |
+
"special": true
|
| 405 |
+
},
|
| 406 |
+
"151693": {
|
| 407 |
+
"content": "<ACTION_TOKEN_6>",
|
| 408 |
+
"lstrip": false,
|
| 409 |
+
"normalized": false,
|
| 410 |
+
"rstrip": false,
|
| 411 |
+
"single_word": false,
|
| 412 |
+
"special": true
|
| 413 |
+
},
|
| 414 |
+
"151694": {
|
| 415 |
+
"content": "<ACTION_TOKEN_7>",
|
| 416 |
+
"lstrip": false,
|
| 417 |
+
"normalized": false,
|
| 418 |
+
"rstrip": false,
|
| 419 |
+
"single_word": false,
|
| 420 |
+
"special": true
|
| 421 |
+
},
|
| 422 |
+
"151695": {
|
| 423 |
+
"content": "<ACTION_TOKEN_8>",
|
| 424 |
+
"lstrip": false,
|
| 425 |
+
"normalized": false,
|
| 426 |
+
"rstrip": false,
|
| 427 |
+
"single_word": false,
|
| 428 |
+
"special": true
|
| 429 |
+
},
|
| 430 |
+
"151696": {
|
| 431 |
+
"content": "<ACTION_TOKEN_9>",
|
| 432 |
+
"lstrip": false,
|
| 433 |
+
"normalized": false,
|
| 434 |
+
"rstrip": false,
|
| 435 |
+
"single_word": false,
|
| 436 |
+
"special": true
|
| 437 |
+
},
|
| 438 |
+
"151697": {
|
| 439 |
+
"content": "<ACTION_TOKEN_10>",
|
| 440 |
+
"lstrip": false,
|
| 441 |
+
"normalized": false,
|
| 442 |
+
"rstrip": false,
|
| 443 |
+
"single_word": false,
|
| 444 |
+
"special": true
|
| 445 |
+
},
|
| 446 |
+
"151698": {
|
| 447 |
+
"content": "<ACTION_TOKEN_11>",
|
| 448 |
+
"lstrip": false,
|
| 449 |
+
"normalized": false,
|
| 450 |
+
"rstrip": false,
|
| 451 |
+
"single_word": false,
|
| 452 |
+
"special": true
|
| 453 |
+
},
|
| 454 |
+
"151699": {
|
| 455 |
+
"content": "<ACTION_TOKEN_12>",
|
| 456 |
+
"lstrip": false,
|
| 457 |
+
"normalized": false,
|
| 458 |
+
"rstrip": false,
|
| 459 |
+
"single_word": false,
|
| 460 |
+
"special": true
|
| 461 |
+
},
|
| 462 |
+
"151700": {
|
| 463 |
+
"content": "<ACTION_TOKEN_13>",
|
| 464 |
+
"lstrip": false,
|
| 465 |
+
"normalized": false,
|
| 466 |
+
"rstrip": false,
|
| 467 |
+
"single_word": false,
|
| 468 |
+
"special": true
|
| 469 |
+
},
|
| 470 |
+
"151701": {
|
| 471 |
+
"content": "<ACTION_TOKEN_14>",
|
| 472 |
+
"lstrip": false,
|
| 473 |
+
"normalized": false,
|
| 474 |
+
"rstrip": false,
|
| 475 |
+
"single_word": false,
|
| 476 |
+
"special": true
|
| 477 |
+
},
|
| 478 |
+
"151702": {
|
| 479 |
+
"content": "<ACTION_TOKEN_15>",
|
| 480 |
+
"lstrip": false,
|
| 481 |
+
"normalized": false,
|
| 482 |
+
"rstrip": false,
|
| 483 |
+
"single_word": false,
|
| 484 |
+
"special": true
|
| 485 |
+
},
|
| 486 |
+
"151703": {
|
| 487 |
+
"content": "<ACTION_TOKEN_16>",
|
| 488 |
+
"lstrip": false,
|
| 489 |
+
"normalized": false,
|
| 490 |
+
"rstrip": false,
|
| 491 |
+
"single_word": false,
|
| 492 |
+
"special": true
|
| 493 |
+
},
|
| 494 |
+
"151704": {
|
| 495 |
+
"content": "<ACTION_TOKEN_17>",
|
| 496 |
+
"lstrip": false,
|
| 497 |
+
"normalized": false,
|
| 498 |
+
"rstrip": false,
|
| 499 |
+
"single_word": false,
|
| 500 |
+
"special": true
|
| 501 |
+
},
|
| 502 |
+
"151705": {
|
| 503 |
+
"content": "<ACTION_TOKEN_18>",
|
| 504 |
+
"lstrip": false,
|
| 505 |
+
"normalized": false,
|
| 506 |
+
"rstrip": false,
|
| 507 |
+
"single_word": false,
|
| 508 |
+
"special": true
|
| 509 |
+
},
|
| 510 |
+
"151706": {
|
| 511 |
+
"content": "<ACTION_TOKEN_19>",
|
| 512 |
+
"lstrip": false,
|
| 513 |
+
"normalized": false,
|
| 514 |
+
"rstrip": false,
|
| 515 |
+
"single_word": false,
|
| 516 |
+
"special": true
|
| 517 |
+
},
|
| 518 |
+
"151707": {
|
| 519 |
+
"content": "<ACTION_TOKEN_20>",
|
| 520 |
+
"lstrip": false,
|
| 521 |
+
"normalized": false,
|
| 522 |
+
"rstrip": false,
|
| 523 |
+
"single_word": false,
|
| 524 |
+
"special": true
|
| 525 |
+
},
|
| 526 |
+
"151708": {
|
| 527 |
+
"content": "<ACTION_TOKEN_21>",
|
| 528 |
+
"lstrip": false,
|
| 529 |
+
"normalized": false,
|
| 530 |
+
"rstrip": false,
|
| 531 |
+
"single_word": false,
|
| 532 |
+
"special": true
|
| 533 |
+
},
|
| 534 |
+
"151709": {
|
| 535 |
+
"content": "<ACTION_TOKEN_22>",
|
| 536 |
+
"lstrip": false,
|
| 537 |
+
"normalized": false,
|
| 538 |
+
"rstrip": false,
|
| 539 |
+
"single_word": false,
|
| 540 |
+
"special": true
|
| 541 |
+
},
|
| 542 |
+
"151710": {
|
| 543 |
+
"content": "<ACTION_TOKEN_23>",
|
| 544 |
+
"lstrip": false,
|
| 545 |
+
"normalized": false,
|
| 546 |
+
"rstrip": false,
|
| 547 |
+
"single_word": false,
|
| 548 |
+
"special": true
|
| 549 |
+
},
|
| 550 |
+
"151711": {
|
| 551 |
+
"content": "<ACTION_TOKEN_24>",
|
| 552 |
+
"lstrip": false,
|
| 553 |
+
"normalized": false,
|
| 554 |
+
"rstrip": false,
|
| 555 |
+
"single_word": false,
|
| 556 |
+
"special": true
|
| 557 |
+
},
|
| 558 |
+
"151712": {
|
| 559 |
+
"content": "<ACTION_TOKEN_25>",
|
| 560 |
+
"lstrip": false,
|
| 561 |
+
"normalized": false,
|
| 562 |
+
"rstrip": false,
|
| 563 |
+
"single_word": false,
|
| 564 |
+
"special": true
|
| 565 |
+
},
|
| 566 |
+
"151713": {
|
| 567 |
+
"content": "<ACTION_TOKEN_26>",
|
| 568 |
+
"lstrip": false,
|
| 569 |
+
"normalized": false,
|
| 570 |
+
"rstrip": false,
|
| 571 |
+
"single_word": false,
|
| 572 |
+
"special": true
|
| 573 |
+
},
|
| 574 |
+
"151714": {
|
| 575 |
+
"content": "<ACTION_TOKEN_27>",
|
| 576 |
+
"lstrip": false,
|
| 577 |
+
"normalized": false,
|
| 578 |
+
"rstrip": false,
|
| 579 |
+
"single_word": false,
|
| 580 |
+
"special": true
|
| 581 |
+
},
|
| 582 |
+
"151715": {
|
| 583 |
+
"content": "<ACTION_TOKEN_28>",
|
| 584 |
+
"lstrip": false,
|
| 585 |
+
"normalized": false,
|
| 586 |
+
"rstrip": false,
|
| 587 |
+
"single_word": false,
|
| 588 |
+
"special": true
|
| 589 |
+
},
|
| 590 |
+
"151716": {
|
| 591 |
+
"content": "<ACTION_TOKEN_29>",
|
| 592 |
+
"lstrip": false,
|
| 593 |
+
"normalized": false,
|
| 594 |
+
"rstrip": false,
|
| 595 |
+
"single_word": false,
|
| 596 |
+
"special": true
|
| 597 |
+
},
|
| 598 |
+
"151717": {
|
| 599 |
+
"content": "<ACTION_TOKEN_30>",
|
| 600 |
+
"lstrip": false,
|
| 601 |
+
"normalized": false,
|
| 602 |
+
"rstrip": false,
|
| 603 |
+
"single_word": false,
|
| 604 |
+
"special": true
|
| 605 |
+
},
|
| 606 |
+
"151718": {
|
| 607 |
+
"content": "<ACTION_TOKEN_31>",
|
| 608 |
+
"lstrip": false,
|
| 609 |
+
"normalized": false,
|
| 610 |
+
"rstrip": false,
|
| 611 |
+
"single_word": false,
|
| 612 |
+
"special": true
|
| 613 |
+
}
|
| 614 |
+
},
|
| 615 |
+
"additional_special_tokens": [
|
| 616 |
+
"<|im_start|>",
|
| 617 |
+
"<|im_end|>",
|
| 618 |
+
"<|object_ref_start|>",
|
| 619 |
+
"<|object_ref_end|>",
|
| 620 |
+
"<|box_start|>",
|
| 621 |
+
"<|box_end|>",
|
| 622 |
+
"<|quad_start|>",
|
| 623 |
+
"<|quad_end|>",
|
| 624 |
+
"<|vision_start|>",
|
| 625 |
+
"<|vision_end|>",
|
| 626 |
+
"<|vision_pad|>",
|
| 627 |
+
"<|image_pad|>",
|
| 628 |
+
"<|video_pad|>",
|
| 629 |
+
"<img>",
|
| 630 |
+
"</img>",
|
| 631 |
+
"<IMG_CONTEXT>",
|
| 632 |
+
"<quad>",
|
| 633 |
+
"</quad>",
|
| 634 |
+
"<ref>",
|
| 635 |
+
"</ref>",
|
| 636 |
+
"<box>",
|
| 637 |
+
"</box>"
|
| 638 |
+
],
|
| 639 |
+
"bos_token": null,
|
| 640 |
+
"clean_up_tokenization_spaces": false,
|
| 641 |
+
"eos_token": "<|im_end|>",
|
| 642 |
+
"errors": "replace",
|
| 643 |
+
"extra_special_tokens": {},
|
| 644 |
+
"model_max_length": 14588,
|
| 645 |
+
"pad_token": "<|endoftext|>",
|
| 646 |
+
"processor_class": "InternVLProcessor",
|
| 647 |
+
"split_special_tokens": false,
|
| 648 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 649 |
+
"unk_token": null
|
| 650 |
+
}
|
pretrained/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
robocasa/added_tokens.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</box>": 151677,
|
| 3 |
+
"</img>": 151670,
|
| 4 |
+
"</quad>": 151673,
|
| 5 |
+
"</ref>": 151675,
|
| 6 |
+
"</think>": 151668,
|
| 7 |
+
"</tool_call>": 151658,
|
| 8 |
+
"</tool_response>": 151666,
|
| 9 |
+
"<ACTION_TOKEN_0>": 151687,
|
| 10 |
+
"<ACTION_TOKEN_1>": 151688,
|
| 11 |
+
"<ACTION_TOKEN_2>": 151689,
|
| 12 |
+
"<ACTION_TOKEN_3>": 151690,
|
| 13 |
+
"<ACTION_TOKEN_4>": 151691,
|
| 14 |
+
"<ACTION_TOKEN_5>": 151692,
|
| 15 |
+
"<ACTION_TOKEN_6>": 151693,
|
| 16 |
+
"<ACTION_TOKEN_7>": 151694,
|
| 17 |
+
"<IMG_CONTEXT>": 151671,
|
| 18 |
+
"<PROP_CONTEXT>": 151686,
|
| 19 |
+
"<box>": 151676,
|
| 20 |
+
"<img>": 151669,
|
| 21 |
+
"<quad>": 151672,
|
| 22 |
+
"<ref>": 151674,
|
| 23 |
+
"<think>": 151667,
|
| 24 |
+
"<tool_call>": 151657,
|
| 25 |
+
"<tool_response>": 151665,
|
| 26 |
+
"<vision_end>": 151679,
|
| 27 |
+
"<vision_start>": 151678,
|
| 28 |
+
"<|action_end|>": 151683,
|
| 29 |
+
"<|action_start|>": 151682,
|
| 30 |
+
"<|box_end|>": 151649,
|
| 31 |
+
"<|box_start|>": 151648,
|
| 32 |
+
"<|endoftext|>": 151643,
|
| 33 |
+
"<|file_sep|>": 151664,
|
| 34 |
+
"<|fim_middle|>": 151660,
|
| 35 |
+
"<|fim_pad|>": 151662,
|
| 36 |
+
"<|fim_prefix|>": 151659,
|
| 37 |
+
"<|fim_suffix|>": 151661,
|
| 38 |
+
"<|im_end|>": 151645,
|
| 39 |
+
"<|im_start|>": 151644,
|
| 40 |
+
"<|image_pad|>": 151655,
|
| 41 |
+
"<|object_ref_end|>": 151647,
|
| 42 |
+
"<|object_ref_start|>": 151646,
|
| 43 |
+
"<|quad_end|>": 151651,
|
| 44 |
+
"<|quad_start|>": 151650,
|
| 45 |
+
"<|repo_name|>": 151663,
|
| 46 |
+
"<|state_end|>": 151685,
|
| 47 |
+
"<|state_start|>": 151684,
|
| 48 |
+
"<|tac_end|>": 151681,
|
| 49 |
+
"<|tac_start|>": 151680,
|
| 50 |
+
"<|video_pad|>": 151656,
|
| 51 |
+
"<|vision_end|>": 151653,
|
| 52 |
+
"<|vision_pad|>": 151654,
|
| 53 |
+
"<|vision_start|>": 151652
|
| 54 |
+
}
|
robocasa/chat_template.jinja
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{{'<|im_start|>' + message['role'] + '
|
| 2 |
+
'}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<image>
|
| 3 |
+
' }}{% elif content['type'] == 'video' %}{{ '<video>
|
| 4 |
+
' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>
|
| 5 |
+
'}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
|
| 6 |
+
' }}{% endif %}
|
robocasa/config.json
ADDED
|
@@ -0,0 +1,366 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"return_dict": true,
|
| 3 |
+
"output_hidden_states": false,
|
| 4 |
+
"torchscript": false,
|
| 5 |
+
"dtype": null,
|
| 6 |
+
"pruned_heads": {},
|
| 7 |
+
"tie_word_embeddings": true,
|
| 8 |
+
"chunk_size_feed_forward": 0,
|
| 9 |
+
"is_encoder_decoder": false,
|
| 10 |
+
"is_decoder": false,
|
| 11 |
+
"cross_attention_hidden_size": null,
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"tie_encoder_decoder": false,
|
| 14 |
+
"architectures": null,
|
| 15 |
+
"finetuning_task": null,
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "LABEL_0",
|
| 18 |
+
"1": "LABEL_1"
|
| 19 |
+
},
|
| 20 |
+
"label2id": {
|
| 21 |
+
"LABEL_0": 0,
|
| 22 |
+
"LABEL_1": 1
|
| 23 |
+
},
|
| 24 |
+
"task_specific_params": null,
|
| 25 |
+
"problem_type": null,
|
| 26 |
+
"tokenizer_class": null,
|
| 27 |
+
"prefix": null,
|
| 28 |
+
"bos_token_id": null,
|
| 29 |
+
"pad_token_id": null,
|
| 30 |
+
"eos_token_id": null,
|
| 31 |
+
"sep_token_id": null,
|
| 32 |
+
"decoder_start_token_id": null,
|
| 33 |
+
"max_length": 20,
|
| 34 |
+
"min_length": 0,
|
| 35 |
+
"do_sample": false,
|
| 36 |
+
"early_stopping": false,
|
| 37 |
+
"num_beams": 1,
|
| 38 |
+
"temperature": 1.0,
|
| 39 |
+
"top_k": 50,
|
| 40 |
+
"top_p": 1.0,
|
| 41 |
+
"typical_p": 1.0,
|
| 42 |
+
"repetition_penalty": 1.0,
|
| 43 |
+
"length_penalty": 1.0,
|
| 44 |
+
"no_repeat_ngram_size": 0,
|
| 45 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 46 |
+
"bad_words_ids": null,
|
| 47 |
+
"num_return_sequences": 1,
|
| 48 |
+
"output_scores": false,
|
| 49 |
+
"return_dict_in_generate": false,
|
| 50 |
+
"forced_bos_token_id": null,
|
| 51 |
+
"forced_eos_token_id": null,
|
| 52 |
+
"remove_invalid_values": false,
|
| 53 |
+
"exponential_decay_length_penalty": null,
|
| 54 |
+
"suppress_tokens": null,
|
| 55 |
+
"begin_suppress_tokens": null,
|
| 56 |
+
"num_beam_groups": 1,
|
| 57 |
+
"diversity_penalty": 0.0,
|
| 58 |
+
"_name_or_path": "",
|
| 59 |
+
"transformers_version": "4.57.1",
|
| 60 |
+
"use_mpg": false,
|
| 61 |
+
"mpg_num_projections": 32,
|
| 62 |
+
"mpg_lambda": 0.1,
|
| 63 |
+
"mpg_use_stop_gradient": true,
|
| 64 |
+
"mpg_refinement_iters": 1,
|
| 65 |
+
"mpg_gate_temperature": 1.0,
|
| 66 |
+
"use_training_time_rtc": false,
|
| 67 |
+
"simulated_delay": 0,
|
| 68 |
+
"rtc_delay_exp_weight": true,
|
| 69 |
+
"use_inference_prefix_overwrite": true,
|
| 70 |
+
"tf_legacy_loss": false,
|
| 71 |
+
"use_bfloat16": false,
|
| 72 |
+
"llm_config": {
|
| 73 |
+
"vocab_size": 151695,
|
| 74 |
+
"max_position_embeddings": 40960,
|
| 75 |
+
"hidden_size": 2048,
|
| 76 |
+
"intermediate_size": 6144,
|
| 77 |
+
"num_hidden_layers": 28,
|
| 78 |
+
"num_attention_heads": 16,
|
| 79 |
+
"use_sliding_window": false,
|
| 80 |
+
"sliding_window": null,
|
| 81 |
+
"max_window_layers": 28,
|
| 82 |
+
"num_key_value_heads": 8,
|
| 83 |
+
"hidden_act": "silu",
|
| 84 |
+
"initializer_range": 0.02,
|
| 85 |
+
"rms_norm_eps": 1e-06,
|
| 86 |
+
"use_cache": false,
|
| 87 |
+
"rope_theta": 1000000,
|
| 88 |
+
"rope_scaling": null,
|
| 89 |
+
"attention_bias": false,
|
| 90 |
+
"attention_dropout": 0.0,
|
| 91 |
+
"is_causal": true,
|
| 92 |
+
"return_dict": true,
|
| 93 |
+
"output_hidden_states": false,
|
| 94 |
+
"torchscript": false,
|
| 95 |
+
"dtype": "bfloat16",
|
| 96 |
+
"pruned_heads": {},
|
| 97 |
+
"tie_word_embeddings": false,
|
| 98 |
+
"chunk_size_feed_forward": 0,
|
| 99 |
+
"is_encoder_decoder": false,
|
| 100 |
+
"is_decoder": false,
|
| 101 |
+
"cross_attention_hidden_size": null,
|
| 102 |
+
"add_cross_attention": false,
|
| 103 |
+
"tie_encoder_decoder": false,
|
| 104 |
+
"architectures": [
|
| 105 |
+
"Qwen3ForCausalLM"
|
| 106 |
+
],
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"id2label": {
|
| 109 |
+
"0": "LABEL_0",
|
| 110 |
+
"1": "LABEL_1"
|
| 111 |
+
},
|
| 112 |
+
"label2id": {
|
| 113 |
+
"LABEL_0": 0,
|
| 114 |
+
"LABEL_1": 1
|
| 115 |
+
},
|
| 116 |
+
"task_specific_params": null,
|
| 117 |
+
"problem_type": null,
|
| 118 |
+
"tokenizer_class": null,
|
| 119 |
+
"prefix": null,
|
| 120 |
+
"bos_token_id": 151643,
|
| 121 |
+
"pad_token_id": null,
|
| 122 |
+
"eos_token_id": 151645,
|
| 123 |
+
"sep_token_id": null,
|
| 124 |
+
"decoder_start_token_id": null,
|
| 125 |
+
"max_length": 20,
|
| 126 |
+
"min_length": 0,
|
| 127 |
+
"do_sample": false,
|
| 128 |
+
"early_stopping": false,
|
| 129 |
+
"num_beams": 1,
|
| 130 |
+
"temperature": 1.0,
|
| 131 |
+
"top_k": 50,
|
| 132 |
+
"top_p": 1.0,
|
| 133 |
+
"typical_p": 1.0,
|
| 134 |
+
"repetition_penalty": 1.0,
|
| 135 |
+
"length_penalty": 1.0,
|
| 136 |
+
"no_repeat_ngram_size": 0,
|
| 137 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 138 |
+
"bad_words_ids": null,
|
| 139 |
+
"num_return_sequences": 1,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"return_dict_in_generate": false,
|
| 142 |
+
"forced_bos_token_id": null,
|
| 143 |
+
"forced_eos_token_id": null,
|
| 144 |
+
"remove_invalid_values": false,
|
| 145 |
+
"exponential_decay_length_penalty": null,
|
| 146 |
+
"suppress_tokens": null,
|
| 147 |
+
"begin_suppress_tokens": null,
|
| 148 |
+
"num_beam_groups": 1,
|
| 149 |
+
"diversity_penalty": 0.0,
|
| 150 |
+
"_name_or_path": "/root/codespace/checkpoints/Qwen3-1.7B",
|
| 151 |
+
"debug": false,
|
| 152 |
+
"ep_size": 1,
|
| 153 |
+
"head_dim": 128,
|
| 154 |
+
"micro_forward": false,
|
| 155 |
+
"model_type": "qwen3",
|
| 156 |
+
"skip_checkpoint": false,
|
| 157 |
+
"use_deepep": false,
|
| 158 |
+
"tf_legacy_loss": false,
|
| 159 |
+
"use_bfloat16": false,
|
| 160 |
+
"qk_norm": true,
|
| 161 |
+
"layer_module": "Qwen3MoTDecoderLayer",
|
| 162 |
+
"use_mot": true,
|
| 163 |
+
"expert_config": {
|
| 164 |
+
"vocab_size": 151936,
|
| 165 |
+
"max_position_embeddings": 40960,
|
| 166 |
+
"hidden_size": 1024,
|
| 167 |
+
"intermediate_size": 3072,
|
| 168 |
+
"num_hidden_layers": 28,
|
| 169 |
+
"num_attention_heads": 16,
|
| 170 |
+
"use_sliding_window": false,
|
| 171 |
+
"sliding_window": null,
|
| 172 |
+
"max_window_layers": 28,
|
| 173 |
+
"num_key_value_heads": 8,
|
| 174 |
+
"hidden_act": "silu",
|
| 175 |
+
"initializer_range": 0.02,
|
| 176 |
+
"rms_norm_eps": 1e-06,
|
| 177 |
+
"use_cache": true,
|
| 178 |
+
"rope_theta": 1000000,
|
| 179 |
+
"rope_scaling": null,
|
| 180 |
+
"attention_bias": false,
|
| 181 |
+
"attention_dropout": 0.0,
|
| 182 |
+
"is_causal": true,
|
| 183 |
+
"return_dict": true,
|
| 184 |
+
"output_hidden_states": false,
|
| 185 |
+
"torchscript": false,
|
| 186 |
+
"dtype": "bfloat16",
|
| 187 |
+
"pruned_heads": {},
|
| 188 |
+
"tie_word_embeddings": true,
|
| 189 |
+
"chunk_size_feed_forward": 0,
|
| 190 |
+
"is_encoder_decoder": false,
|
| 191 |
+
"is_decoder": false,
|
| 192 |
+
"cross_attention_hidden_size": null,
|
| 193 |
+
"add_cross_attention": false,
|
| 194 |
+
"tie_encoder_decoder": false,
|
| 195 |
+
"architectures": [
|
| 196 |
+
"Qwen3ForCausalLM"
|
| 197 |
+
],
|
| 198 |
+
"finetuning_task": null,
|
| 199 |
+
"id2label": {
|
| 200 |
+
"0": "LABEL_0",
|
| 201 |
+
"1": "LABEL_1"
|
| 202 |
+
},
|
| 203 |
+
"label2id": {
|
| 204 |
+
"LABEL_0": 0,
|
| 205 |
+
"LABEL_1": 1
|
| 206 |
+
},
|
| 207 |
+
"task_specific_params": null,
|
| 208 |
+
"problem_type": null,
|
| 209 |
+
"tokenizer_class": null,
|
| 210 |
+
"prefix": null,
|
| 211 |
+
"bos_token_id": 151643,
|
| 212 |
+
"pad_token_id": null,
|
| 213 |
+
"eos_token_id": 151645,
|
| 214 |
+
"sep_token_id": null,
|
| 215 |
+
"decoder_start_token_id": null,
|
| 216 |
+
"max_length": 20,
|
| 217 |
+
"min_length": 0,
|
| 218 |
+
"do_sample": false,
|
| 219 |
+
"early_stopping": false,
|
| 220 |
+
"num_beams": 1,
|
| 221 |
+
"temperature": 1.0,
|
| 222 |
+
"top_k": 50,
|
| 223 |
+
"top_p": 1.0,
|
| 224 |
+
"typical_p": 1.0,
|
| 225 |
+
"repetition_penalty": 1.0,
|
| 226 |
+
"length_penalty": 1.0,
|
| 227 |
+
"no_repeat_ngram_size": 0,
|
| 228 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 229 |
+
"bad_words_ids": null,
|
| 230 |
+
"num_return_sequences": 1,
|
| 231 |
+
"output_scores": false,
|
| 232 |
+
"return_dict_in_generate": false,
|
| 233 |
+
"forced_bos_token_id": null,
|
| 234 |
+
"forced_eos_token_id": null,
|
| 235 |
+
"remove_invalid_values": false,
|
| 236 |
+
"exponential_decay_length_penalty": null,
|
| 237 |
+
"suppress_tokens": null,
|
| 238 |
+
"begin_suppress_tokens": null,
|
| 239 |
+
"num_beam_groups": 1,
|
| 240 |
+
"diversity_penalty": 0.0,
|
| 241 |
+
"_name_or_path": "",
|
| 242 |
+
"head_dim": 128,
|
| 243 |
+
"model_type": "qwen3",
|
| 244 |
+
"tf_legacy_loss": false,
|
| 245 |
+
"use_bfloat16": false,
|
| 246 |
+
"qk_norm": true,
|
| 247 |
+
"layer_module": "Qwen3DecoderLayer",
|
| 248 |
+
"output_attentions": false
|
| 249 |
+
},
|
| 250 |
+
"attn_implementation": "flash_attention_2",
|
| 251 |
+
"output_attentions": false
|
| 252 |
+
},
|
| 253 |
+
"vit_config": {
|
| 254 |
+
"return_dict": true,
|
| 255 |
+
"output_hidden_states": false,
|
| 256 |
+
"torchscript": false,
|
| 257 |
+
"dtype": "bfloat16",
|
| 258 |
+
"pruned_heads": {},
|
| 259 |
+
"tie_word_embeddings": true,
|
| 260 |
+
"chunk_size_feed_forward": 0,
|
| 261 |
+
"is_encoder_decoder": false,
|
| 262 |
+
"is_decoder": false,
|
| 263 |
+
"cross_attention_hidden_size": null,
|
| 264 |
+
"add_cross_attention": false,
|
| 265 |
+
"tie_encoder_decoder": false,
|
| 266 |
+
"architectures": [
|
| 267 |
+
"InternVisionModel"
|
| 268 |
+
],
|
| 269 |
+
"finetuning_task": null,
|
| 270 |
+
"id2label": {
|
| 271 |
+
"0": "LABEL_0",
|
| 272 |
+
"1": "LABEL_1"
|
| 273 |
+
},
|
| 274 |
+
"label2id": {
|
| 275 |
+
"LABEL_0": 0,
|
| 276 |
+
"LABEL_1": 1
|
| 277 |
+
},
|
| 278 |
+
"task_specific_params": null,
|
| 279 |
+
"problem_type": null,
|
| 280 |
+
"tokenizer_class": null,
|
| 281 |
+
"prefix": null,
|
| 282 |
+
"bos_token_id": null,
|
| 283 |
+
"pad_token_id": null,
|
| 284 |
+
"eos_token_id": null,
|
| 285 |
+
"sep_token_id": null,
|
| 286 |
+
"decoder_start_token_id": null,
|
| 287 |
+
"max_length": 20,
|
| 288 |
+
"min_length": 0,
|
| 289 |
+
"do_sample": false,
|
| 290 |
+
"early_stopping": false,
|
| 291 |
+
"num_beams": 1,
|
| 292 |
+
"temperature": 1.0,
|
| 293 |
+
"top_k": 50,
|
| 294 |
+
"top_p": 1.0,
|
| 295 |
+
"typical_p": 1.0,
|
| 296 |
+
"repetition_penalty": 1.0,
|
| 297 |
+
"length_penalty": 1.0,
|
| 298 |
+
"no_repeat_ngram_size": 0,
|
| 299 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 300 |
+
"bad_words_ids": null,
|
| 301 |
+
"num_return_sequences": 1,
|
| 302 |
+
"output_scores": false,
|
| 303 |
+
"return_dict_in_generate": false,
|
| 304 |
+
"forced_bos_token_id": null,
|
| 305 |
+
"forced_eos_token_id": null,
|
| 306 |
+
"remove_invalid_values": false,
|
| 307 |
+
"exponential_decay_length_penalty": null,
|
| 308 |
+
"suppress_tokens": null,
|
| 309 |
+
"begin_suppress_tokens": null,
|
| 310 |
+
"num_beam_groups": 1,
|
| 311 |
+
"diversity_penalty": 0.0,
|
| 312 |
+
"_name_or_path": "",
|
| 313 |
+
"auto_map": {
|
| 314 |
+
"AutoConfig": "configuration_intern_vit.InternVisionConfig",
|
| 315 |
+
"AutoModel": "modeling_intern_vit.InternVisionModel"
|
| 316 |
+
},
|
| 317 |
+
"model_type": "intern_vit_6b",
|
| 318 |
+
"use_fa3": false,
|
| 319 |
+
"tf_legacy_loss": false,
|
| 320 |
+
"use_bfloat16": false,
|
| 321 |
+
"hidden_size": 1024,
|
| 322 |
+
"intermediate_size": 4096,
|
| 323 |
+
"dropout": 0.0,
|
| 324 |
+
"drop_path_rate": 0.0,
|
| 325 |
+
"num_hidden_layers": 24,
|
| 326 |
+
"num_attention_heads": 16,
|
| 327 |
+
"num_channels": 3,
|
| 328 |
+
"patch_size": 14,
|
| 329 |
+
"image_size": 224,
|
| 330 |
+
"initializer_range": 0.02,
|
| 331 |
+
"initializer_factor": 1.0,
|
| 332 |
+
"attention_dropout": 0.0,
|
| 333 |
+
"layer_norm_eps": 1e-06,
|
| 334 |
+
"hidden_act": "gelu",
|
| 335 |
+
"norm_type": "layer_norm",
|
| 336 |
+
"qkv_bias": true,
|
| 337 |
+
"qk_normalization": false,
|
| 338 |
+
"use_flash_attn": true,
|
| 339 |
+
"select_layer": -1,
|
| 340 |
+
"downsample_ratio": 0.5,
|
| 341 |
+
"output_attentions": false
|
| 342 |
+
},
|
| 343 |
+
"connector_arch": "internvl_connector",
|
| 344 |
+
"template": "being_h0",
|
| 345 |
+
"select_layer": -1,
|
| 346 |
+
"force_image_size": 224,
|
| 347 |
+
"downsample_ratio": 0.5,
|
| 348 |
+
"action_chunk_length": 8,
|
| 349 |
+
"loss_func": "l1",
|
| 350 |
+
"gen_action_type": "prop_hidden",
|
| 351 |
+
"layer_select_for_action": -1,
|
| 352 |
+
"action_token_num": 8,
|
| 353 |
+
"learnable_action_query": false,
|
| 354 |
+
"prompt_template": "long",
|
| 355 |
+
"use_expert": true,
|
| 356 |
+
"use_flow_matching": true,
|
| 357 |
+
"attn_mode": "causal",
|
| 358 |
+
"max_num_embodiments": 32,
|
| 359 |
+
"noise_beta_alpha": 1.5,
|
| 360 |
+
"noise_beta_beta": 1.0,
|
| 361 |
+
"num_timestep_buckets": 1000,
|
| 362 |
+
"noise_s": 0.999,
|
| 363 |
+
"num_inference_timesteps": 4,
|
| 364 |
+
"model_type": "beingh",
|
| 365 |
+
"output_attentions": false
|
| 366 |
+
}
|
robocasa/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
robocasa/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:828dbd203933b4c8f219ecb1e977b14332fe1a0fd3d47b51bf41031c03002ec7
|
| 3 |
+
size 11201369880
|
robocasa/robocasa_human_posttrain_metadata.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
robocasa/special_tokens_map.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>",
|
| 16 |
+
"<img>",
|
| 17 |
+
"</img>",
|
| 18 |
+
"<IMG_CONTEXT>",
|
| 19 |
+
"<quad>",
|
| 20 |
+
"</quad>",
|
| 21 |
+
"<ref>",
|
| 22 |
+
"</ref>",
|
| 23 |
+
"<box>",
|
| 24 |
+
"</box>"
|
| 25 |
+
],
|
| 26 |
+
"eos_token": {
|
| 27 |
+
"content": "<|im_end|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"pad_token": {
|
| 34 |
+
"content": "<|endoftext|>",
|
| 35 |
+
"lstrip": false,
|
| 36 |
+
"normalized": false,
|
| 37 |
+
"rstrip": false,
|
| 38 |
+
"single_word": false
|
| 39 |
+
}
|
| 40 |
+
}
|
robocasa/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12806c7c382822e3b8215170269ab902ff55298f14b3578a02436dde5f7c1d84
|
| 3 |
+
size 11427559
|
robocasa/tokenizer_config.json
ADDED
|
@@ -0,0 +1,458 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"151643": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"151644": {
|
| 15 |
+
"content": "<|im_start|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"151645": {
|
| 23 |
+
"content": "<|im_end|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"151646": {
|
| 31 |
+
"content": "<|object_ref_start|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"151647": {
|
| 39 |
+
"content": "<|object_ref_end|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"151648": {
|
| 47 |
+
"content": "<|box_start|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"151649": {
|
| 55 |
+
"content": "<|box_end|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"151650": {
|
| 63 |
+
"content": "<|quad_start|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"151651": {
|
| 71 |
+
"content": "<|quad_end|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"151652": {
|
| 79 |
+
"content": "<|vision_start|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"151653": {
|
| 87 |
+
"content": "<|vision_end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"151654": {
|
| 95 |
+
"content": "<|vision_pad|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"151655": {
|
| 103 |
+
"content": "<|image_pad|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"151656": {
|
| 111 |
+
"content": "<|video_pad|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"151657": {
|
| 119 |
+
"content": "<tool_call>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"151658": {
|
| 127 |
+
"content": "</tool_call>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"151659": {
|
| 135 |
+
"content": "<|fim_prefix|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"151660": {
|
| 143 |
+
"content": "<|fim_middle|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"151661": {
|
| 151 |
+
"content": "<|fim_suffix|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"151662": {
|
| 159 |
+
"content": "<|fim_pad|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"151663": {
|
| 167 |
+
"content": "<|repo_name|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"151664": {
|
| 175 |
+
"content": "<|file_sep|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
},
|
| 182 |
+
"151665": {
|
| 183 |
+
"content": "<tool_response>",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": false,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": false
|
| 189 |
+
},
|
| 190 |
+
"151666": {
|
| 191 |
+
"content": "</tool_response>",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": false,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": false
|
| 197 |
+
},
|
| 198 |
+
"151667": {
|
| 199 |
+
"content": "<think>",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": false
|
| 205 |
+
},
|
| 206 |
+
"151668": {
|
| 207 |
+
"content": "</think>",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": false,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false,
|
| 212 |
+
"special": false
|
| 213 |
+
},
|
| 214 |
+
"151669": {
|
| 215 |
+
"content": "<img>",
|
| 216 |
+
"lstrip": false,
|
| 217 |
+
"normalized": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"single_word": false,
|
| 220 |
+
"special": true
|
| 221 |
+
},
|
| 222 |
+
"151670": {
|
| 223 |
+
"content": "</img>",
|
| 224 |
+
"lstrip": false,
|
| 225 |
+
"normalized": false,
|
| 226 |
+
"rstrip": false,
|
| 227 |
+
"single_word": false,
|
| 228 |
+
"special": true
|
| 229 |
+
},
|
| 230 |
+
"151671": {
|
| 231 |
+
"content": "<IMG_CONTEXT>",
|
| 232 |
+
"lstrip": false,
|
| 233 |
+
"normalized": false,
|
| 234 |
+
"rstrip": false,
|
| 235 |
+
"single_word": false,
|
| 236 |
+
"special": true
|
| 237 |
+
},
|
| 238 |
+
"151672": {
|
| 239 |
+
"content": "<quad>",
|
| 240 |
+
"lstrip": false,
|
| 241 |
+
"normalized": false,
|
| 242 |
+
"rstrip": false,
|
| 243 |
+
"single_word": false,
|
| 244 |
+
"special": true
|
| 245 |
+
},
|
| 246 |
+
"151673": {
|
| 247 |
+
"content": "</quad>",
|
| 248 |
+
"lstrip": false,
|
| 249 |
+
"normalized": false,
|
| 250 |
+
"rstrip": false,
|
| 251 |
+
"single_word": false,
|
| 252 |
+
"special": true
|
| 253 |
+
},
|
| 254 |
+
"151674": {
|
| 255 |
+
"content": "<ref>",
|
| 256 |
+
"lstrip": false,
|
| 257 |
+
"normalized": false,
|
| 258 |
+
"rstrip": false,
|
| 259 |
+
"single_word": false,
|
| 260 |
+
"special": true
|
| 261 |
+
},
|
| 262 |
+
"151675": {
|
| 263 |
+
"content": "</ref>",
|
| 264 |
+
"lstrip": false,
|
| 265 |
+
"normalized": false,
|
| 266 |
+
"rstrip": false,
|
| 267 |
+
"single_word": false,
|
| 268 |
+
"special": true
|
| 269 |
+
},
|
| 270 |
+
"151676": {
|
| 271 |
+
"content": "<box>",
|
| 272 |
+
"lstrip": false,
|
| 273 |
+
"normalized": false,
|
| 274 |
+
"rstrip": false,
|
| 275 |
+
"single_word": false,
|
| 276 |
+
"special": true
|
| 277 |
+
},
|
| 278 |
+
"151677": {
|
| 279 |
+
"content": "</box>",
|
| 280 |
+
"lstrip": false,
|
| 281 |
+
"normalized": false,
|
| 282 |
+
"rstrip": false,
|
| 283 |
+
"single_word": false,
|
| 284 |
+
"special": true
|
| 285 |
+
},
|
| 286 |
+
"151678": {
|
| 287 |
+
"content": "<vision_start>",
|
| 288 |
+
"lstrip": false,
|
| 289 |
+
"normalized": false,
|
| 290 |
+
"rstrip": false,
|
| 291 |
+
"single_word": false,
|
| 292 |
+
"special": true
|
| 293 |
+
},
|
| 294 |
+
"151679": {
|
| 295 |
+
"content": "<vision_end>",
|
| 296 |
+
"lstrip": false,
|
| 297 |
+
"normalized": false,
|
| 298 |
+
"rstrip": false,
|
| 299 |
+
"single_word": false,
|
| 300 |
+
"special": true
|
| 301 |
+
},
|
| 302 |
+
"151680": {
|
| 303 |
+
"content": "<|tac_start|>",
|
| 304 |
+
"lstrip": false,
|
| 305 |
+
"normalized": false,
|
| 306 |
+
"rstrip": false,
|
| 307 |
+
"single_word": false,
|
| 308 |
+
"special": true
|
| 309 |
+
},
|
| 310 |
+
"151681": {
|
| 311 |
+
"content": "<|tac_end|>",
|
| 312 |
+
"lstrip": false,
|
| 313 |
+
"normalized": false,
|
| 314 |
+
"rstrip": false,
|
| 315 |
+
"single_word": false,
|
| 316 |
+
"special": true
|
| 317 |
+
},
|
| 318 |
+
"151682": {
|
| 319 |
+
"content": "<|action_start|>",
|
| 320 |
+
"lstrip": false,
|
| 321 |
+
"normalized": false,
|
| 322 |
+
"rstrip": false,
|
| 323 |
+
"single_word": false,
|
| 324 |
+
"special": true
|
| 325 |
+
},
|
| 326 |
+
"151683": {
|
| 327 |
+
"content": "<|action_end|>",
|
| 328 |
+
"lstrip": false,
|
| 329 |
+
"normalized": false,
|
| 330 |
+
"rstrip": false,
|
| 331 |
+
"single_word": false,
|
| 332 |
+
"special": true
|
| 333 |
+
},
|
| 334 |
+
"151684": {
|
| 335 |
+
"content": "<|state_start|>",
|
| 336 |
+
"lstrip": false,
|
| 337 |
+
"normalized": false,
|
| 338 |
+
"rstrip": false,
|
| 339 |
+
"single_word": false,
|
| 340 |
+
"special": true
|
| 341 |
+
},
|
| 342 |
+
"151685": {
|
| 343 |
+
"content": "<|state_end|>",
|
| 344 |
+
"lstrip": false,
|
| 345 |
+
"normalized": false,
|
| 346 |
+
"rstrip": false,
|
| 347 |
+
"single_word": false,
|
| 348 |
+
"special": true
|
| 349 |
+
},
|
| 350 |
+
"151686": {
|
| 351 |
+
"content": "<PROP_CONTEXT>",
|
| 352 |
+
"lstrip": false,
|
| 353 |
+
"normalized": false,
|
| 354 |
+
"rstrip": false,
|
| 355 |
+
"single_word": false,
|
| 356 |
+
"special": true
|
| 357 |
+
},
|
| 358 |
+
"151687": {
|
| 359 |
+
"content": "<ACTION_TOKEN_0>",
|
| 360 |
+
"lstrip": false,
|
| 361 |
+
"normalized": false,
|
| 362 |
+
"rstrip": false,
|
| 363 |
+
"single_word": false,
|
| 364 |
+
"special": true
|
| 365 |
+
},
|
| 366 |
+
"151688": {
|
| 367 |
+
"content": "<ACTION_TOKEN_1>",
|
| 368 |
+
"lstrip": false,
|
| 369 |
+
"normalized": false,
|
| 370 |
+
"rstrip": false,
|
| 371 |
+
"single_word": false,
|
| 372 |
+
"special": true
|
| 373 |
+
},
|
| 374 |
+
"151689": {
|
| 375 |
+
"content": "<ACTION_TOKEN_2>",
|
| 376 |
+
"lstrip": false,
|
| 377 |
+
"normalized": false,
|
| 378 |
+
"rstrip": false,
|
| 379 |
+
"single_word": false,
|
| 380 |
+
"special": true
|
| 381 |
+
},
|
| 382 |
+
"151690": {
|
| 383 |
+
"content": "<ACTION_TOKEN_3>",
|
| 384 |
+
"lstrip": false,
|
| 385 |
+
"normalized": false,
|
| 386 |
+
"rstrip": false,
|
| 387 |
+
"single_word": false,
|
| 388 |
+
"special": true
|
| 389 |
+
},
|
| 390 |
+
"151691": {
|
| 391 |
+
"content": "<ACTION_TOKEN_4>",
|
| 392 |
+
"lstrip": false,
|
| 393 |
+
"normalized": false,
|
| 394 |
+
"rstrip": false,
|
| 395 |
+
"single_word": false,
|
| 396 |
+
"special": true
|
| 397 |
+
},
|
| 398 |
+
"151692": {
|
| 399 |
+
"content": "<ACTION_TOKEN_5>",
|
| 400 |
+
"lstrip": false,
|
| 401 |
+
"normalized": false,
|
| 402 |
+
"rstrip": false,
|
| 403 |
+
"single_word": false,
|
| 404 |
+
"special": true
|
| 405 |
+
},
|
| 406 |
+
"151693": {
|
| 407 |
+
"content": "<ACTION_TOKEN_6>",
|
| 408 |
+
"lstrip": false,
|
| 409 |
+
"normalized": false,
|
| 410 |
+
"rstrip": false,
|
| 411 |
+
"single_word": false,
|
| 412 |
+
"special": true
|
| 413 |
+
},
|
| 414 |
+
"151694": {
|
| 415 |
+
"content": "<ACTION_TOKEN_7>",
|
| 416 |
+
"lstrip": false,
|
| 417 |
+
"normalized": false,
|
| 418 |
+
"rstrip": false,
|
| 419 |
+
"single_word": false,
|
| 420 |
+
"special": true
|
| 421 |
+
}
|
| 422 |
+
},
|
| 423 |
+
"additional_special_tokens": [
|
| 424 |
+
"<|im_start|>",
|
| 425 |
+
"<|im_end|>",
|
| 426 |
+
"<|object_ref_start|>",
|
| 427 |
+
"<|object_ref_end|>",
|
| 428 |
+
"<|box_start|>",
|
| 429 |
+
"<|box_end|>",
|
| 430 |
+
"<|quad_start|>",
|
| 431 |
+
"<|quad_end|>",
|
| 432 |
+
"<|vision_start|>",
|
| 433 |
+
"<|vision_end|>",
|
| 434 |
+
"<|vision_pad|>",
|
| 435 |
+
"<|image_pad|>",
|
| 436 |
+
"<|video_pad|>",
|
| 437 |
+
"<img>",
|
| 438 |
+
"</img>",
|
| 439 |
+
"<IMG_CONTEXT>",
|
| 440 |
+
"<quad>",
|
| 441 |
+
"</quad>",
|
| 442 |
+
"<ref>",
|
| 443 |
+
"</ref>",
|
| 444 |
+
"<box>",
|
| 445 |
+
"</box>"
|
| 446 |
+
],
|
| 447 |
+
"bos_token": null,
|
| 448 |
+
"clean_up_tokenization_spaces": false,
|
| 449 |
+
"eos_token": "<|im_end|>",
|
| 450 |
+
"errors": "replace",
|
| 451 |
+
"extra_special_tokens": {},
|
| 452 |
+
"model_max_length": 14588,
|
| 453 |
+
"pad_token": "<|endoftext|>",
|
| 454 |
+
"processor_class": "InternVLProcessor",
|
| 455 |
+
"split_special_tokens": false,
|
| 456 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 457 |
+
"unk_token": null
|
| 458 |
+
}
|
robocasa/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|