{ "architectures": [ "MixtralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 15, "eos_token_id": 16, "head_dim": null, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.01, "intermediate_size": 8192, "iter": 133393, "max_position_embeddings": 8192, "model_type": "mixtral", "num_attention_heads": 16, "num_experts_per_tok": 2, "num_hidden_layers": 12, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "pad_token_id": 14, "rms_norm_eps": 1e-05, "rope_theta": 50000000, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.52.4", "use_cache": true, "vocab_size": 256 }