{ "_name_or_path": "/home/taishi/workspace/drop-upcycle/checkpoints/upcycle-Mixtral-8x1.56B-shuffle_torch_rand_002_random_rand_init_0.50_noise", "architectures": [ "MixtralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 7168, "max_position_embeddings": 4096, "model_type": "mixtral", "num_attention_heads": 16, "num_experts_per_tok": 2, "num_hidden_layers": 24, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": true, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "router_aux_loss_coef": 0.02, "router_jitter_noise": 0.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.46.2", "use_cache": true, "vocab_size": 48640 }