config.json

{
  "_name_or_path": "/data5/models/Qwen2.5-32B-Instruct",
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 27648,
  "max_position_embeddings": 32768,
  "max_window_layers": 70,
  "model_type": "qwen2",
  "num_attention_heads": 40,
  "num_hidden_layers": 64,
  "num_key_value_heads": 8,
  "quantization_config": {
    "amp": true,
    "autoround_version": "0.4.0.dev",
    "backend": "auto_round:gptq:exllamav2",
    "batch_size": 8,
    "bits": 4,
    "data_type": "int",
    "dataset": "NeelNanda/pile-10k",
    "enable_minmax_tuning": true,
    "enable_norm_bias_tuning": false,
    "enable_quanted_input": true,
    "extra_config": {
      "model.layers.5.mlp.down_proj": {
        "bits": 16,
        "data_type": "float"
      },
      "model.layers.5.mlp.gate_proj": {
        "bits": 16,
        "data_type": "float"
      },
      "model.layers.5.mlp.up_proj": {
        "bits": 16,
        "data_type": "float"
      }
    },
    "gradient_accumulate_steps": 1,
    "group_size": 128,
    "iters": 1000,
    "low_gpu_mem_usage": false,
    "lr": 0.001,
    "minmax_lr": 0.001,
    "nsamples": 512,
    "quant_block_list": null,
    "quant_method": "intel/auto-round",
    "scale_dtype": "torch.float16",
    "seqlen": 2048,
    "sym": true
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.46.1",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 152064
}