Upload folder using huggingface_hub

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen2_5_VisionTransformerPretrainedModel"
+  ],
+  "depth": 32,
+  "fullatt_block_indexes": [
+    7,
+    15,
+    23,
+    31
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 1280,
+  "in_channels": 3,
+  "in_chans": 3,
+  "intermediate_size": 3456,
+  "initializer_range": 0.02,
+  "_attn_implementation": "flash_attention_2",
+  "model_type": "qwen2_5_vl",
+  "num_heads": 16,
+  "out_hidden_size": 5120,
+  "patch_size": 14,
+  "spatial_merge_size": 2,
+  "spatial_patch_size": 14,
+  "temporal_patch_size": 2,
+  "tokens_per_second": 2,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "window_size": 112
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8c395ee35705fd885fb9bc283cc9e7e150e75c76012041107f7c9bbb71f38e2
+size 1377722984

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "min_pixels": 3136,
+  "max_pixels": 12845056,
+  "patch_size": 14,
+  "temporal_patch_size": 2,
+  "merge_size": 2,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "processor_class": "Qwen2_5_VLProcessor"
+}