| { |
| "architectures": [ |
| "EsmcForMaskedLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "modeling_esmc_remote.EsmcRemoteConfig", |
| "AutoModel": "modeling_esmc_remote.EsmcRemoteModel", |
| "AutoModelForMaskedLM": "modeling_esmc_remote.EsmcRemoteForMaskedLM", |
| "AutoModelForSequenceClassification": "modeling_esmc_remote.EsmcRemoteForSequenceClassification", |
| "AutoModelForTokenClassification": "modeling_esmc_remote.EsmcRemoteForTokenClassification" |
| }, |
| "bos_token_id": 0, |
| "classifier_dropout": 0.1, |
| "dtype": "float32", |
| "eos_token_id": 2, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 2560, |
| "initializer_range": 0.02, |
| "intermediate_size": 6912, |
| "mask_token_id": 32, |
| "max_position_embeddings": 2048, |
| "mlp_bias": false, |
| "model_type": "esmc", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 80, |
| "num_key_value_heads": 40, |
| "pad_token_id": 1, |
| "rope_parameters": { |
| "rope_theta": 10000.0, |
| "rope_type": "default" |
| }, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.16.0.dev0", |
| "vocab_size": 64 |
| } |
|
|
