| { |
| "architectures": [ |
| "EsmForMaskedLM" |
| ], |
| "attention_probs_dropout_prob": 0.0, |
| "batch_size": 96, |
| "classifier_dropout": null, |
| "d_ff": 3072, |
| "emb_layer_norm_before": false, |
| "esmfold_config": null, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.0, |
| "hidden_size": 320, |
| "initializer_range": 0.02, |
| "intermediate_size": 1280, |
| "is_folding_model": false, |
| "layer_norm_eps": 1e-05, |
| "mask_token_id": 32, |
| "max_len": 150, |
| "max_position_embeddings": 130, |
| "max_steps": 225000, |
| "model_type": "esm", |
| "num_attention_heads": 20, |
| "num_hidden_layers": 6, |
| "pad_token_id": 1, |
| "peak_learning_rate": 0.0001, |
| "position_embedding_type": "rotary", |
| "token_dropout": true, |
| "torch_dtype": "float32", |
| "transformers_version": "4.39.3", |
| "use_cache": true, |
| "vocab_list": null, |
| "vocab_size": 33, |
| "weight_decay": 0.01 |
| } |
|
|
