{ "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2", "activation_function": "gelu", "architectures": [ "MistralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 50256, "eos_token_id": 50256, "gradient_checkpointing": true, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 16384, "layer_norm_epsilon": 1e-05, "max_position_embeddings": 1024, "model_type": "mistral", "num_attention_heads": 16, "num_hidden_layers": 32, "num_key_value_heads": 8, "pad_token_id": 50256, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.41.2", "use_cache": false, "vocab_size": 32000 }