| { | |
| "_name_or_path": "/mnt/azureml/cr/j/7b8a43d845bf4e97a460239351ad8c16/cap/data-capability/wd/INPUT_decec8c7b73544729e93ada53f8fd315_xrag/projects/xRAG/pretrained_model/sfr-mistral-7b", | |
| "architectures": [ | |
| "XMistralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "projector_type": "mlp2x_gelu", | |
| "retriever_hidden_size": 4096, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.38.0", | |
| "use_cache": true, | |
| "vocab_size": 32002 | |
| } | |