First model version

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.safetensors* filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "Qwen2VisionTransformerPretrainedModel"
+  ],
+  "vision_config": {
+	"depth": 32,
+  	"embed_dim": 1280,
+  	"hidden_act": "quick_gelu",
+  	"hidden_size": 3584,
+  	"in_channels": 3,
+  	"in_chans": 3,
+  	"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"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:571d794b5614851cd52b423dadab31dbeeb3aca41eb706524ba65c30c8208605
+size 1351555936

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": "Qwen2VLProcessor"
+}