config.json

{
  "_name_or_path": "/root/quantized/Nous-Hermes-2-Mixtral-8x7B-DPO-GPTQ-4bit-128g-actorder_False/",
  "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,
  "quantization_config": {
    "batch_size": 1,
    "bits": 4,
    "block_name_to_quantize": null,
    "cache_block_outputs": true,
    "damp_percent": 0.01,
    "dataset": null,
    "desc_act": false,
    "exllama_config": {
      "version": 1
    },
    "group_size": 128,
    "max_input_length": null,
    "model_seqlen": null,
    "module_name_preceding_first_block": null,
    "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.0.w2",
        "block_sparse_moe.experts.0.w3"
      ],
      [
        "block_sparse_moe.experts.1.w1",
        "block_sparse_moe.experts.1.w2",
        "block_sparse_moe.experts.1.w3"
      ],
      [
        "block_sparse_moe.experts.2.w1",
        "block_sparse_moe.experts.2.w2",
        "block_sparse_moe.experts.2.w3"
      ],
      [
        "block_sparse_moe.experts.3.w1",
        "block_sparse_moe.experts.3.w2",
        "block_sparse_moe.experts.3.w3"
      ],
      [
        "block_sparse_moe.experts.4.w1",
        "block_sparse_moe.experts.4.w2",
        "block_sparse_moe.experts.4.w3"
      ],
      [
        "block_sparse_moe.experts.5.w1",
        "block_sparse_moe.experts.5.w2",
        "block_sparse_moe.experts.5.w3"
      ],
      [
        "block_sparse_moe.experts.6.w1",
        "block_sparse_moe.experts.6.w2",
        "block_sparse_moe.experts.6.w3"
      ],
      [
        "block_sparse_moe.experts.7.w1",
        "block_sparse_moe.experts.7.w2",
        "block_sparse_moe.experts.7.w3"
      ]
    ],
    "pad_token_id": null,
    "quant_method": "gptq",
    "sym": true,
    "tokenizer": null,
    "true_sequential": true,
    "use_cuda_fp16": false,
    "use_exllama": true
  },
  "rms_norm_eps": 1e-05,
  "rope_theta": 1000000.0,
  "router_aux_loss_coef": 0.02,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.38.2",
  "use_cache": false,
  "vocab_size": 32002
}