| { | |
| "architectures": [ | |
| "EsmForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "classifier_dropout": null, | |
| "emb_layer_norm_before": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 10240, | |
| "layer_norm_eps": 1e-05, | |
| "mask_token_id": 32, | |
| "max_position_embeddings": 1026, | |
| "model_type": "esm", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 36, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "rotary", | |
| "token_dropout": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.23.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 33 | |
| } | |