Update README.md

README.md

@@ -29,20 +29,7 @@ For example, DSE-QWen2-2b-MRL-V1 achieves **85.8** nDCG@5 on [ViDoRE](https://hu
 
 
 ## Note:
-The following steps need to be done before running the code:
-1. clone latest transformers, `git clone https://github.com/huggingface/transformers.git`
-2. Fix a bug in `transformers/models/qwen2_vl/modeling_qwen2_vl.py` around line 1774
-```
-position_ids = position_ids.unsqueeze(0).expand(3, -1, -1)
-# change the if statement below to if cache_position is not None and cache_position[0] != 0:
-if cache_position[0] != 0:
-    pixel_values = None
-    pixel_values_videos = None
-```
-3. Install latest transformers from source `pip install -e .`
-4. `pip install qwen-vl-utils`
-
-> QWen vision encoder may take high GPU memory if the input image is large. Adjust  `'resized_height':680 , 'resized_width':680` (see below) to fit VRAM based on GPU resources.
+QWen vision encoder may take high GPU memory if the input image is large. Adjust  `'resized_height':680 , 'resized_width':680` (see below) to fit VRAM based on GPU resources.
 
 ## How to Use the Model
 
@@ -96,7 +83,8 @@ query_texts = [
 ]
 query_image_inputs, query_video_inputs = process_vision_info(query_messages)
 query_inputs = processor(text=query_texts, images=query_image_inputs, videos=query_video_inputs, padding='longest', return_tensors='pt').to('cuda:0')
-query_inputs = model.prepare_inputs_for_generation(**query_inputs, use_cache=False)
+cache_position = torch.arange(0, len(query_texts))
+query_inputs = model.prepare_inputs_for_generation(**query_inputs, cache_position=cache_position, use_cache=False)
 with torch.no_grad():
   output = model(**query_inputs, return_dict=True, output_hidden_states=True)
 query_embeddings = get_embedding(output.hidden_states[-1], 1536) # adjust dimensionality for efficiency trade-off, e.g. 512
@@ -138,7 +126,8 @@ doc_texts = [
 ]
 doc_image_inputs, doc_video_inputs = process_vision_info(doc_messages)
 doc_inputs = processor(text=doc_texts, images=doc_image_inputs, videos=doc_video_inputs, padding='longest', return_tensors='pt').to('cuda:0')
-doc_inputs = model.prepare_inputs_for_generation(**doc_inputs, use_cache=False)
+cache_position = torch.arange(0, len(doc_texts))
+doc_inputs = model.prepare_inputs_for_generation(**doc_inputs, cache_position=cache_position, use_cache=False)
 output = model(**doc_inputs, return_dict=True, output_hidden_states=True)
 with torch.no_grad():
     output = model(**doc_inputs, return_dict=True, output_hidden_states=True)
@@ -184,7 +173,8 @@ doc_texts = [
 ]
 doc_image_inputs, doc_video_inputs = process_vision_info(doc_messages)
 doc_inputs = processor(text=doc_texts, images=doc_image_inputs, videos=doc_video_inputs, padding='longest', return_tensors='pt').to('cuda:0')
-doc_inputs = model.prepare_inputs_for_generation(**doc_inputs, use_cache=False)
+cache_position = torch.arange(0, len(doc_texts))
+doc_inputs = model.prepare_inputs_for_generation(**doc_inputs, cache_position=cache_position, use_cache=False)
 output = model(**doc_inputs, return_dict=True, output_hidden_states=True)
 with torch.no_grad():
     output = model(**doc_inputs, return_dict=True, output_hidden_states=True)