config.json

{
  "architectures": [
    "Qwen2VisionTransformerPretrainedModel"
  ],
  "vision_config": {
	  "depth": 32,
	  "embed_dim": 1280,
	  "hidden_act": "quick_gelu",
	  "hidden_size": 1536,
	  "in_channels": 3,
	  "in_chans": 3,
	  "initializer_range": 0.02,
	  "mlp_ratio": 4,
	  "num_heads": 16,
	  "patch_size": 14,
	  "spatial_merge_size": 2,
	  "spatial_patch_size": 14,
	  "temporal_patch_size": 2,
	  "initializer_range": 0.02,
	  "_attn_implementation": "flash_attention_2"
  },
  "model_type": "qwen2_vl",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.45.0"
}