config.json

{
  "architectures": [
    "HawkQwenForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 1536,
  "image_token_id": 151655,
  "initializer_range": 0.02,
  "intermediate_size": 8960,
  "max_position_embeddings": 32768,
  "max_window_layers": 21,
  "mm_vision_tower": "/home/gpu-admin/workspace/models/Qwen2-VL-ViT",
  "model_type": "hawk_vl",
  "num_attention_heads": 12,
  "num_hidden_layers": 28,
  "num_key_value_heads": 2,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": 32768,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.43.1",
  "use_cache": true,
  "use_sliding_window": false,
  "video_token_id": 151656,
  "vision_config": {
    "_attn_implementation_autoset": false,
    "_name_or_path": "/home/gpu-admin/workspace/models/Qwen2-VL-ViT",
    "add_cross_attention": false,
    "architectures": [
      "QwenVisionModel"
    ],
    "auto_map": {
      "AutoConfig": "configuration_qwen_vit.QwenVisionConfig",
      "AutoModel": "modeling_qwen_vit.QwenVisionModel"
    },
    "depth": 32,
    "embed_dim": 1280,
    "hidden_act": "quick_gelu",
    "in_channels": 3,
    "lm_hidden_size": 1536,
    "mlp_ratio": 4,
    "mm_projector_type": "pixel_unshuffle",
    "model_type": "qwen_vit",
    "num_heads": 16,
    "patch_size": 14,
    "spatial_merge_size": 2,
    "temporal_patch_size": 2,
    "torch_dtype": "bfloat16"
  },
  "vision_end_id": 151653,
  "vision_start_id": 151652,
  "vocab_size": 151665
}