| { | |
| "_name_or_path": "None", | |
| "architectures": [ | |
| "LlamaEncForMaskedLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_llama_enc.LlamaEncConfig", | |
| "AutoModel": "modeling_llama_enc.LlamaEncModel", | |
| "AutoModelForMaskedLM": "modeling_llama_enc.LlamaEncForMaskedLM", | |
| "AutoModelForQuestionAnswering": "modeling_llama_enc.LlamaEncForQuestionAnswering", | |
| "AutoModelForSequenceClassification": "modeling_llama_enc.LlamaEncForSequenceClassification", | |
| "AutoModelForTokenClassification": "modeling_llama_enc.LlamaEncForTokenClassification" | |
| }, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "label_smoothing": 0.0, | |
| "max_position_embeddings": 8192, | |
| "mlp_bias": false, | |
| "model_type": "llama_enc", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 20000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.41.2", | |
| "trust_remote_code": true, | |
| "use_cache": true, | |
| "vocab_size": 99584, | |
| "window_size_left": -1, | |
| "window_size_right": -1 | |
| } | |