config.json

{
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 27648,
  "max_position_embeddings": 40960,
  "max_window_layers": 64,
  "model_type": "qwen2",
  "num_attention_heads": 40,
  "num_hidden_layers": 64,
  "num_key_value_heads": 8,
  "quantization_config": {
    "bits": 8,
    "checkpoint_format": "gptq",
    "desc_act": true,
    "group_size": 128,
    "lm_head": false,
    "meta": {
      "damp_auto_increment": 0.0025,
      "damp_percent": 0.01,
      "mse": 0.0,
      "quantizer": [
        "gptqmodel:2.2.0"
      ],
      "static_groups": false,
      "true_sequential": true,
      "uri": "https://github.com/modelcloud/gptqmodel"
    },
    "pack_dtype": "int32",
    "quant_method": "gptq",
    "sym": true
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.1",
  "use_cache": false,
  "use_sliding_window": false,
  "vocab_size": 152064
}