{ "architectures": [ "MistralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 1, "dtype": "float32", "eos_token_id": 2, "head_dim": 64, "hidden_act": "silu", "hidden_size": 384, "initializer_range": 0.02, "intermediate_size": 1536, "max_position_embeddings": 512, "model_type": "mistral", "num_attention_heads": 6, "num_hidden_layers": 8, "num_key_value_heads": 2, "pad_token_id": 0, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 10000.0, "rope_type": "default" }, "sliding_window": 4096, "tie_word_embeddings": true, "transformers_version": "5.2.0", "use_cache": true, "vocab_size": 16384 }