config.json

{
  "_name_or_path": "Qwen/QwQ-32B-Preview",
  "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": 64,
  "model_type": "qwen2",
  "num_attention_heads": 40,
  "num_hidden_layers": 64,
  "num_key_value_heads": 8,
  "pad_token_id": 151654,
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": true,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": [
      "lm_head",
      "multi_modal_projector",
      "merger",
      "modality_projection",
      "model.layers.0.self_attn",
      "model.layers.1.self_attn",
      "model.layers.2.self_attn",
      "model.layers.3.self_attn",
      "model.layers.4.self_attn",
      "model.layers.5.self_attn",
      "model.layers.6.self_attn",
      "model.layers.7.self_attn",
      "model.layers.8.self_attn",
      "model.layers.9.self_attn",
      "model.layers.10.self_attn",
      "model.layers.11.self_attn",
      "model.layers.12.self_attn",
      "model.layers.13.self_attn",
      "model.layers.14.self_attn",
      "model.layers.15.self_attn",
      "model.layers.16.self_attn",
      "model.layers.17.self_attn",
      "model.layers.18.self_attn",
      "model.layers.19.self_attn",
      "model.layers.20.self_attn",
      "model.layers.21.self_attn",
      "model.layers.22.self_attn",
      "model.layers.23.self_attn",
      "model.layers.24.self_attn",
      "model.layers.25.self_attn",
      "model.layers.26.self_attn",
      "model.layers.27.self_attn",
      "model.layers.28.self_attn",
      "model.layers.29.self_attn",
      "model.layers.30.self_attn",
      "model.layers.31.self_attn",
      "model.layers.32.self_attn",
      "model.layers.33.self_attn",
      "model.layers.34.self_attn",
      "model.layers.35.self_attn",
      "model.layers.36.self_attn",
      "model.layers.37.self_attn",
      "model.layers.38.self_attn",
      "model.layers.39.self_attn",
      "model.layers.40.self_attn",
      "model.layers.41.self_attn",
      "model.layers.42.self_attn",
      "model.layers.43.self_attn",
      "model.layers.44.self_attn",
      "model.layers.45.self_attn",
      "model.layers.46.self_attn",
      "model.layers.47.self_attn",
      "model.layers.48.self_attn",
      "model.layers.49.self_attn",
      "model.layers.50.self_attn",
      "model.layers.51.self_attn",
      "model.layers.52.self_attn",
      "model.layers.53.self_attn",
      "model.layers.54.self_attn",
      "model.layers.55.self_attn",
      "model.layers.56.self_attn",
      "model.layers.57.self_attn",
      "model.layers.58.self_attn",
      "model.layers.59.self_attn",
      "model.layers.60.self_attn",
      "model.layers.61.self_attn",
      "model.layers.62.self_attn",
      "model.layers.63.self_attn"
    ],
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.46.3",
  "unsloth_fixed": true,
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 152064
}