Instructions to use kuleshov-group/e2d2-cnndm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kuleshov-group/e2d2-cnndm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="kuleshov-group/e2d2-cnndm", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("kuleshov-group/e2d2-cnndm", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download generation_config.json from kuleshov-group/e2d2-cnndm: direct link, hf CLI and curl.
- Browser
- Download file 427 Bytes
-
https://huggingface.co/kuleshov-group/e2d2-cnndm/resolve/main/generation_config.json
- Command line
-
hf download hf://kuleshov-group/e2d2-cnndm/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/kuleshov-group/e2d2-cnndm/resolve/main/generation_config.json
427 Bytes
| { | |
| "align_inputs_to_blocks": false, | |
| "block_size": 8, | |
| "bos_token_id": 151643, | |
| "confidence_based_noising": true, | |
| "confidence_margin_based_noising": false, | |
| "confidence_threshold": 1000000.0, | |
| "eos_token_id": 151643, | |
| "first_hitting": true, | |
| "min_t": 1e-05, | |
| "num_steps": 8, | |
| "pad_token_id": 151643, | |
| "sampling_strategy": "predict_and_noise", | |
| "transformers_version": "4.52.3", | |
| "use_model_output_cache": true | |
| } | |