{ "_name_or_path": "mistralai/Mixtral-8x22B-Instruct-v0.1", "architectures": [ "MixtralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 6144, "initializer_range": 0.02, "intermediate_size": 16384, "max_position_embeddings": 65536, "model_type": "mixtral", "num_attention_heads": 48, "num_experts_per_tok": 2, "num_hidden_layers": 56, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "quantization_config": { "activation_scheme": "static", "ignored_layers": [ "model.layers.55.block_sparse_moe.gate", "model.layers.0.block_sparse_moe.gate", "model.layers.36.block_sparse_moe.gate", "model.layers.2.block_sparse_moe.gate", "model.layers.8.block_sparse_moe.gate", "model.layers.40.block_sparse_moe.gate", "model.layers.11.block_sparse_moe.gate", "model.layers.15.block_sparse_moe.gate", "model.layers.23.block_sparse_moe.gate", "model.layers.10.block_sparse_moe.gate", "model.layers.7.block_sparse_moe.gate", "model.layers.38.block_sparse_moe.gate", "model.layers.43.block_sparse_moe.gate", "model.layers.53.block_sparse_moe.gate", "model.layers.1.block_sparse_moe.gate", "model.layers.37.block_sparse_moe.gate", "model.layers.54.block_sparse_moe.gate", "model.layers.24.block_sparse_moe.gate", "model.layers.28.block_sparse_moe.gate", "model.layers.41.block_sparse_moe.gate", "model.layers.17.block_sparse_moe.gate", "model.layers.45.block_sparse_moe.gate", "model.layers.6.block_sparse_moe.gate", "model.layers.20.block_sparse_moe.gate", "model.layers.25.block_sparse_moe.gate", "model.layers.34.block_sparse_moe.gate", "model.layers.12.block_sparse_moe.gate", "model.layers.26.block_sparse_moe.gate", "model.layers.50.block_sparse_moe.gate", "lm_head", "model.layers.19.block_sparse_moe.gate", "model.layers.48.block_sparse_moe.gate", "model.layers.33.block_sparse_moe.gate", "model.layers.4.block_sparse_moe.gate", "model.layers.29.block_sparse_moe.gate", "model.layers.44.block_sparse_moe.gate", "model.layers.16.block_sparse_moe.gate", "model.layers.42.block_sparse_moe.gate", "model.layers.30.block_sparse_moe.gate", "model.layers.51.block_sparse_moe.gate", "model.layers.21.block_sparse_moe.gate", "model.layers.18.block_sparse_moe.gate", "model.layers.32.block_sparse_moe.gate", "model.layers.35.block_sparse_moe.gate", "model.layers.49.block_sparse_moe.gate", "model.layers.14.block_sparse_moe.gate", "model.layers.31.block_sparse_moe.gate", "model.layers.47.block_sparse_moe.gate", "model.layers.22.block_sparse_moe.gate", "model.layers.3.block_sparse_moe.gate", "model.layers.46.block_sparse_moe.gate", "model.layers.9.block_sparse_moe.gate", "model.layers.13.block_sparse_moe.gate", "model.layers.39.block_sparse_moe.gate", "model.layers.52.block_sparse_moe.gate", "model.layers.5.block_sparse_moe.gate", "model.layers.27.block_sparse_moe.gate" ], "quant_method": "fp8" }, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.41.2", "use_cache": true, "vocab_size": 32768 }