{ "architectures": [ "MixtralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 1, "dtype": "float32", "eos_token_id": 2, "head_dim": null, "hidden_act": "silu", "hidden_size": 128, "initializer_range": 0.02, "intermediate_size": 352, "max_position_embeddings": 4096, "model_type": "mixtral", "num_attention_heads": 2, "num_experts_per_tok": 2, "num_hidden_layers": 3, "num_key_value_heads": 2, "num_local_experts": 4, "output_router_logits": false, "pad_token_id": 2, "rms_norm_eps": 1e-05, "rope_parameters": { "rope_theta": 15000.0, "rope_type": "default" }, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "sliding_window": null, "tie_word_embeddings": false, "transformers_version": "5.9.0", "use_cache": false, "vocab_size": 512 }