{ "_name_or_path": "/workspace/process/nousresearch_nous-hermes-2-mixtral-8x7b-dpo/source", "architectures": [ "MixtralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mixtral", "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 32, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "router_aux_loss_coef": 0.02, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.37.0.dev0", "use_cache": true, "vocab_size": 32002, "quantization_config": { "bits": 4, "group_size": -1, "damp_percent": 0.1, "desc_act": true, "static_groups": false, "sym": true, "true_sequential": true, "model_name_or_path": null, "model_file_base_name": "model", "quant_method": "gptq", "modules_in_block_to_quantize": [ [ "self_attn.k_proj", "self_attn.v_proj", "self_attn.q_proj" ], [ "self_attn.o_proj" ], [ "block_sparse_moe.experts.0.w1", "block_sparse_moe.experts.1.w1", "block_sparse_moe.experts.2.w1", "block_sparse_moe.experts.3.w1", "block_sparse_moe.experts.4.w1", "block_sparse_moe.experts.5.w1", "block_sparse_moe.experts.6.w1", "block_sparse_moe.experts.7.w1", "block_sparse_moe.experts.0.w3", "block_sparse_moe.experts.1.w3", "block_sparse_moe.experts.2.w3", "block_sparse_moe.experts.3.w3", "block_sparse_moe.experts.4.w3", "block_sparse_moe.experts.5.w3", "block_sparse_moe.experts.6.w3", "block_sparse_moe.experts.7.w3" ], [ "block_sparse_moe.experts.0.w2", "block_sparse_moe.experts.1.w2", "block_sparse_moe.experts.2.w2", "block_sparse_moe.experts.3.w2", "block_sparse_moe.experts.4.w2", "block_sparse_moe.experts.5.w2", "block_sparse_moe.experts.6.w2", "block_sparse_moe.experts.7.w2" ] ] } }