| { | |
| "architectures": [ | |
| "ESMplusplusForMaskedLM" | |
| ], | |
| "attn_backend": "sdpa", | |
| "auto_map": { | |
| "AutoConfig": "modeling_esm_plusplus.ESMplusplusConfig", | |
| "AutoModel": "modeling_esm_plusplus.ESMplusplusModel", | |
| "AutoModelForMaskedLM": "modeling_esm_plusplus.ESMplusplusForMaskedLM", | |
| "AutoModelForSequenceClassification": "modeling_esm_plusplus.ESMplusplusForSequenceClassification", | |
| "AutoModelForTokenClassification": "modeling_esm_plusplus.ESMplusplusForTokenClassification" | |
| }, | |
| "dropout": 0.0, | |
| "dtype": "float32", | |
| "hidden_size": 1152, | |
| "initializer_range": 0.02, | |
| "model_type": "ESMplusplus", | |
| "num_attention_heads": 18, | |
| "num_hidden_layers": 36, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.2.0", | |
| "vocab_size": 64 | |
| } | |