{ "architectures": [ "MixtralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 1, "dtype": "float32", "eos_token_id": 2, "head_dim": null, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 4096, "iter": 213247, "max_position_embeddings": 1048576, "model_type": "mixtral", "num_attention_heads": 16, "num_experts_per_tok": 2, "num_hidden_layers": 12, "num_key_value_heads": 8, "num_local_experts": 32, "output_router_logits": false, "pad_token_id": 3, "rms_norm_eps": 1e-05, "rope_theta": 50000000, "router_aux_loss_coef": 0.01, "router_jitter_noise": 0.0, "sliding_window": null, "tie_word_embeddings": false, "transformers_version": "4.56.2", "use_cache": true, "vocab_size": 256 }