Qwen2.5-VL-7B-Instruct

Running on Zero

htian01 commited on 6 days ago

Commit

3fb0bbe

verified ·

1 Parent(s): aa5e815

Update app.py

Files changed (1) hide show

app.py CHANGED Viewed

@@ -98,7 +98,7 @@ def model_inference(input_dict, history):
         return_tensors="pt",
         padding=True,
     ).to("cuda")
-    streamer = TextIteratorStreamer(processor, skip_prompt=True, skip_special_tokens=False)
     generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=4096)
     thread = Thread(target=model.generate, kwargs=generation_kwargs)
     thread.start()

         return_tensors="pt",
         padding=True,
     ).to("cuda")
+    streamer = TextIteratorStreamer(processor, skip_prompt=True, skip_special_tokens=True)
     generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=4096)
     thread = Thread(target=model.generate, kwargs=generation_kwargs)
     thread.start()