{ "_name_or_path": "/notebooks/moe-8x7b", "architectures": [ "MixtralForCausalLM" ], "attention_bias": true, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 32768, "model_type": "mixtral", "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 32, "num_key_value_heads": 32, "num_local_experts": 8, "output_router_logits": false, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "router_aux_loss_coef": 0.001, "sliding_window": 8192, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.36.1", "use_cache": true, "vocab_size": 151936 }