{ "architectures": [ "MixtralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 1152, "max_position_embeddings": 32768, "model_type": "mixtral", "num_attention_heads": 32, "num_experts_per_tok": 8, "num_hidden_layers": 32, "num_key_value_heads": 8, "num_local_experts": 64, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 16000000.0, "router_aux_loss_coef": 0.005, "router_jitter_noise": 0.0, "scoring_func": "softmax", "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.47.0.dev0", "use_cache": true, "vocab_size": 128256 }