{ "architectures": [ "MixtralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 640, "initializer_range": 0.02, "intermediate_size": 2400, "max_position_embeddings": 131072, "model_type": "mixtral", "num_attention_heads": 8, "num_experts_per_tok": 2, "num_hidden_layers": 8, "num_key_value_heads": 4, "num_local_experts": 6, "output_router_logits": true, "pad_token_id": 0, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "router_aux_loss_coef": 0.001, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.37.0", "use_cache": true, "vocab_size": 35000 }