Instructions to use mgh6/TCS_MLM_SaProt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mgh6/TCS_MLM_SaProt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="mgh6/TCS_MLM_SaProt")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("mgh6/TCS_MLM_SaProt") model = AutoModelForMaskedLM.from_pretrained("mgh6/TCS_MLM_SaProt", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from mgh6/TCS_MLM_SaProt: direct link, hf CLI and curl.
- Browser
- Download file 771 Bytes
-
https://huggingface.co/mgh6/TCS_MLM_SaProt/resolve/5d2affef4c81b7f43715c84ee06830e80098b7e4/config.json
- Command line
-
hf download hf://mgh6/TCS_MLM_SaProt@5d2affef4c81b7f43715c84ee06830e80098b7e4/config.json
-
curl -L -o config.json https://huggingface.co/mgh6/TCS_MLM_SaProt/resolve/5d2affef4c81b7f43715c84ee06830e80098b7e4/config.json
771 Bytes
| { | |
| "_name_or_path": "westlake-repl/SaProt_650M_PDB", | |
| "architectures": [ | |
| "EsmForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "classifier_dropout": null, | |
| "emb_layer_norm_before": false, | |
| "esmfold_config": null, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 1280, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5120, | |
| "is_folding_model": false, | |
| "layer_norm_eps": 1e-05, | |
| "mask_token_id": 4, | |
| "max_position_embeddings": 1026, | |
| "model_type": "esm", | |
| "num_attention_heads": 20, | |
| "num_hidden_layers": 33, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "rotary", | |
| "token_dropout": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.42.3", | |
| "use_cache": true, | |
| "vocab_list": null, | |
| "vocab_size": 446 | |
| } | |