{ "architectures": [ "MixtralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 0, "dtype": "float32", "eos_token_id": 0, "head_dim": null, "hidden_act": "silu", "hidden_size": 512, "initializer_range": 0.02, "intermediate_size": 1536, "max_position_embeddings": 2048, "model_type": "mixtral", "num_attention_heads": 8, "num_experts_per_tok": 2, "num_hidden_layers": 12, "num_key_value_heads": 4, "num_local_experts": 4, "output_router_logits": false, "pad_token_id": 0, "rms_norm_eps": 1e-05, "rope_parameters": { "rope_theta": 10000.0, "rope_type": "default" }, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "sliding_window": 1024, "tie_word_embeddings": false, "transformers_version": "5.7.0", "use_cache": false, "vocab_size": 50304 }