config.json

{
  "_name_or_path": "/data5/models//Qwen2-VL-72B-Instruct",
  "architectures": [
    "Qwen2VLForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "image_token_id": 151655,
  "initializer_range": 0.02,
  "intermediate_size": 29568,
  "max_position_embeddings": 32768,
  "max_window_layers": 80,
  "model_type": "qwen2_vl",
  "num_attention_heads": 64,
  "num_hidden_layers": 80,
  "num_key_value_heads": 8,
  "quantization_config": {
    "amp": true,
    "autoround_version": "0.4.2.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,
    "gradient_accumulate_steps": 1,
    "group_size": 128,
    "iters": 1000,
    "low_gpu_mem_usage": true,
    "lr": 0.001,
    "minmax_lr": 0.001,
    "nsamples": 512,
    "quant_method": "intel/auto-round",
    "scale_dtype": "torch.float16",
    "seqlen": 2048,
    "sym": true,
    "to_quant_block_names": "model.layers"
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": {
    "mrope_section": [
      16,
      24,
      24
    ],
    "rope_type": "default",
    "type": "default"
  },
  "rope_theta": 1000000.0,
  "sliding_window": 32768,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.47.0",
  "use_cache": true,
  "use_sliding_window": false,
  "video_token_id": 151656,
  "vision_config": {
    "hidden_size": 8192,
    "in_chans": 3,
    "model_type": "qwen2_vl",
    "spatial_patch_size": 14
  },
  "vision_end_token_id": 151653,
  "vision_start_token_id": 151652,
  "vision_token_id": 151654,
  "vocab_size": 152064
}