Update app.py

app.py

@@ -1,27 +1,20 @@
-from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
+import torch
+from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
 from qwen_vl_utils import process_vision_info
 
-# default: Load the model on the available device(s)
+# Check if CUDA is available and set the device accordingly
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+# Load the model on the available device
 model = Qwen2VLForConditionalGeneration.from_pretrained(
     "Qwen/Qwen2-VL-2B-Instruct", torch_dtype="auto", device_map="auto"
 )
+model = model.to(device)
 
-# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
-# model = Qwen2VLForConditionalGeneration.from_pretrained(
-#     "Qwen/Qwen2-VL-2B-Instruct",
-#     torch_dtype=torch.bfloat16,
-#     attn_implementation="flash_attention_2",
-#     device_map="auto",
-# )
-
-# default processer
+# Default processor
 processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct")
 
-# The default range for the number of visual tokens per image in the model is 4-16384. You can set min_pixels and max_pixels according to your needs, such as a token count range of 256-1280, to balance speed and memory usage.
-# min_pixels = 256*28*28
-# max_pixels = 1280*28*28
-# processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)
-
+# Prepare input messages
 messages = [
     {
         "role": "user",
@@ -47,14 +40,20 @@ inputs = processor(
     padding=True,
     return_tensors="pt",
 )
-inputs = inputs.to("cuda")
+inputs = inputs.to(device)  # Move inputs to the same device as the model
 
 # Inference: Generation of the output
 generated_ids = model.generate(**inputs, max_new_tokens=128)
+
+# Trim the output tokens
 generated_ids_trimmed = [
-    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+    out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
 ]
+
+# Decode the generated text
 output_text = processor.batch_decode(
     generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
 )
-print(output_text)
+
+# Print the output
+print(output_text)