config.json

{
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "dtype": "bfloat16",
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 896,
  "initializer_range": 0.02,
  "intermediate_size": 4864,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 32768,
  "max_window_layers": 21,
  "model_type": "qwen2",
  "num_attention_heads": 14,
  "num_hidden_layers": 24,
  "num_key_value_heads": 2,
  "pad_token_id": 151662,
  "quantization_config": {
    "bits": 4,
    "checkpoint_format": "gptq",
    "desc_act": false,
    "group_size": 32,
    "lm_head": false,
    "meta": {
      "act_group_aware": true,
      "damp_auto_increment": 0.01,
      "damp_percent": 0.05,
      "mse": 0.0,
      "quantizer": [
        "gptqmodel:5.0.0-dev0"
      ],
      "static_groups": false,
      "true_sequential": true,
      "uri": "https://github.com/modelcloud/gptqmodel",
      "v2": false,
      "v2_alpha": 0.25
    },
    "pack_dtype": "int32",
    "pack_impl": "cpu",
    "quant_method": "gptq",
    "sym": true
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": true,
  "transformers_version": "4.57.1",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}