| { | |
| "architectures": [ | |
| "EsmcForTokenClassification" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "classifier_dropout": 0.1, | |
| "dtype": "float32", | |
| "eos_token_id": 2, | |
| "head_dim": 8, | |
| "hidden_act": "silu", | |
| "hidden_size": 32, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1", | |
| "2": "LABEL_2" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 64, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1, | |
| "LABEL_2": 2 | |
| }, | |
| "mask_token_id": 32, | |
| "max_position_embeddings": 2048, | |
| "mlp_bias": false, | |
| "model_type": "esmc", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 2, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": 1, | |
| "rope_parameters": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.19.0.dev0", | |
| "vocab_size": 33 | |
| } | |