| { | |
| "add_bias_fnn": false, | |
| "architectures": [ | |
| "EsmForMaskedLM", | |
| "EsmForTokenClassification", | |
| "EsmForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "esm_config.EsmConfig", | |
| "AutoModelForMaskedLM": "modeling_esm.EsmForMaskedLM", | |
| "AutoModelForTokenClassification": "modeling_esm.EsmForTokenClassification", | |
| "AutoModelForSequenceClassification": "modeling_esm.EsmForSequenceClassification" | |
| }, | |
| "emb_layer_norm_before": false, | |
| "esmfold_config": null, | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "is_folding_model": false, | |
| "layer_norm_eps": 1e-12, | |
| "mask_token_id": 2, | |
| "max_position_embeddings": 2050, | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 29, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "rotary", | |
| "tie_word_embeddings": false, | |
| "token_dropout": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.32.0.dev0", | |
| "use_cache": false, | |
| "vocab_list": null, | |
| "vocab_size": 4107 | |
| } | |