{ "architectures": [ "MixtralForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 31989, "eos_token_id": 31989, "head_dim": 64, "hidden_act": "silu", "hidden_size": 768, "initializer_range": 0.036084391824351615, "intermediate_size": 1920, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "mixtral", "num_attention_heads": 12, "num_experts_per_tok": 2, "num_hidden_layers": 27, "num_key_value_heads": 4, "num_local_experts": 7, "output_router_logits": false, "pad_token_id": 31989, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "sliding_window": null, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.53.3", "use_cache": false, "vocab_size": 32000 }