Model save
Browse files- README.md +2 -2
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- config.json +81 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -4,8 +4,8 @@ library_name: transformers
|
|
| 4 |
model_name: Qwen2.5-3B-Instruct-SFT
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
- sft
|
| 8 |
- trl
|
|
|
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
|
@@ -27,7 +27,7 @@ print(output["generated_text"])
|
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
| 30 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/walks/huggingface/runs/
|
| 31 |
|
| 32 |
|
| 33 |
This model was trained with SFT.
|
|
|
|
| 4 |
model_name: Qwen2.5-3B-Instruct-SFT
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
| 7 |
- trl
|
| 8 |
+
- sft
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
|
|
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
| 30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/walks/huggingface/runs/54e1zct5)
|
| 31 |
|
| 32 |
|
| 33 |
This model was trained with SFT.
|
adapter_config.json
CHANGED
|
@@ -25,12 +25,12 @@
|
|
| 25 |
"rank_pattern": {},
|
| 26 |
"revision": null,
|
| 27 |
"target_modules": [
|
| 28 |
-
"down_proj",
|
| 29 |
-
"gate_proj",
|
| 30 |
-
"v_proj",
|
| 31 |
"up_proj",
|
|
|
|
| 32 |
"q_proj",
|
|
|
|
| 33 |
"o_proj",
|
|
|
|
| 34 |
"k_proj"
|
| 35 |
],
|
| 36 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 25 |
"rank_pattern": {},
|
| 26 |
"revision": null,
|
| 27 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
| 28 |
"up_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
"q_proj",
|
| 31 |
+
"down_proj",
|
| 32 |
"o_proj",
|
| 33 |
+
"gate_proj",
|
| 34 |
"k_proj"
|
| 35 |
],
|
| 36 |
"task_type": "CAUSAL_LM",
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 119801528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92354c006341b1e40cccb66eeddd961992916aebc74f57b16476485c0bbb9399
|
| 3 |
size 119801528
|
config.json
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 2048,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"layer_types": [
|
| 13 |
+
"full_attention",
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention"
|
| 49 |
+
],
|
| 50 |
+
"max_position_embeddings": 32768,
|
| 51 |
+
"max_window_layers": 70,
|
| 52 |
+
"model_type": "qwen2",
|
| 53 |
+
"num_attention_heads": 16,
|
| 54 |
+
"num_hidden_layers": 36,
|
| 55 |
+
"num_key_value_heads": 2,
|
| 56 |
+
"quantization_config": {
|
| 57 |
+
"_load_in_4bit": true,
|
| 58 |
+
"_load_in_8bit": false,
|
| 59 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 60 |
+
"bnb_4bit_quant_storage": "bfloat16",
|
| 61 |
+
"bnb_4bit_quant_type": "nf4",
|
| 62 |
+
"bnb_4bit_use_double_quant": false,
|
| 63 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 64 |
+
"llm_int8_has_fp16_weight": false,
|
| 65 |
+
"llm_int8_skip_modules": null,
|
| 66 |
+
"llm_int8_threshold": 6.0,
|
| 67 |
+
"load_in_4bit": true,
|
| 68 |
+
"load_in_8bit": false,
|
| 69 |
+
"quant_method": "bitsandbytes"
|
| 70 |
+
},
|
| 71 |
+
"rms_norm_eps": 1e-06,
|
| 72 |
+
"rope_scaling": null,
|
| 73 |
+
"rope_theta": 1000000.0,
|
| 74 |
+
"sliding_window": null,
|
| 75 |
+
"tie_word_embeddings": true,
|
| 76 |
+
"torch_dtype": "bfloat16",
|
| 77 |
+
"transformers_version": "4.55.2",
|
| 78 |
+
"use_cache": true,
|
| 79 |
+
"use_sliding_window": false,
|
| 80 |
+
"vocab_size": 151936
|
| 81 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6673
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d1cc73962fc3af5f40bdd49375b15a8552503fbade42febe4b8096adfbe4b1c
|
| 3 |
size 6673
|