fix

modelscope · Dec 24, 2024 · 44e793d · 44e793d
1 parent cb8d2bb
commit 44e793d
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 3 deletions.
diff --git a/examples/train/multimodal/ocr.sh b/examples/train/multimodal/ocr.sh
@@ -22,4 +22,4 @@ swift sft \
     --max_length 2048 \
     --output_dir output \
     --warmup_ratio 0.05 \
-    --dataloader_num_workers 4
+    --dataloader_num_workers 4
diff --git a/swift/llm/template/template/qwen.py b/swift/llm/template/template/qwen.py
@@ -198,10 +198,12 @@ def _encode(self, inputs: StdTemplateInputs) -> Dict[str, Any]:
             if locals()[media_type]:
                 if media_type == 'images':
                     media_token = self.image_token_id
-                    media_inputs = processor.image_processor(images=images, videos=None, return_tensors='pt')
+                    media_inputs = processor.image_processor(
+                        images=images, videos=None, return_tensors='pt', do_rescale=False)
                     media_grid_thw = media_inputs['image_grid_thw']
                 else:
-                    media_inputs = processor.image_processor(images=None, videos=videos, return_tensors='pt')
+                    media_inputs = processor.image_processor(
+                        images=None, videos=videos, return_tensors='pt', do_rescale=False)
                     media_grid_thw = media_inputs['video_grid_thw']
                     media_token = self.video_token_id
                 idx_list = findall(input_ids, media_token)