| { |
| "add_bias_fnn": false, |
| "architectures": [ |
| "EsmForSequenceClassification" |
| ], |
| "attention_probs_dropout_prob": 0.0, |
| "auto_map": { |
| "AutoConfig": "esm_config.EsmConfig", |
| "AutoModelForMaskedLM": "modeling_esm.EsmForMaskedLM", |
| "AutoModelForSequenceClassification": "modeling_esm.EsmForSequenceClassification", |
| "AutoModelForTokenClassification": "modeling_esm.EsmForTokenClassification" |
| }, |
| "dtype": "float32", |
| "emb_layer_norm_before": false, |
| "esmfold_config": null, |
| "hidden_dropout_prob": 0.0, |
| "hidden_size": 1024, |
| "id2label": { |
| "0": "LABEL_0" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "is_folding_model": false, |
| "label2id": { |
| "LABEL_0": 0 |
| }, |
| "layer_norm_eps": 1e-12, |
| "mask_token_id": 2, |
| "max_position_embeddings": 2050, |
| "model_type": "esm", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 29, |
| "pad_token_id": 1, |
| "position_embedding_type": "rotary", |
| "problem_type": "regression", |
| "tie_word_embeddings": false, |
| "token_dropout": false, |
| "transformers_version": "4.57.6", |
| "use_cache": false, |
| "vocab_list": null, |
| "vocab_size": 4107 |
| } |
|
|
