Qwen2.5-VL-7B-Instruct

Running on Zero

htian01 commited on 27 days ago

Commit

2630ff3

verified ·

1 Parent(s): d26d037

Update app.py

Files changed (1) hide show

app.py CHANGED Viewed

@@ -102,7 +102,7 @@ def model_inference(input_dict, history):
             padding=True,
         ).to("cuda")
         # Set up streaming generation.
-        streamer = TextIteratorStreamer(processor, skip_prompt=True, skip_special_tokens=True)
         generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=1024)
         thread = Thread(target=model.generate, kwargs=generation_kwargs)
         thread.start()
@@ -144,7 +144,7 @@ def model_inference(input_dict, history):
         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=1024)
     thread = Thread(target=model.generate, kwargs=generation_kwargs)
     thread.start()

             padding=True,
         ).to("cuda")
         # Set up streaming generation.
+        streamer = TextIteratorStreamer(processor, skip_prompt=True, skip_special_tokens=False)
         generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=1024)
         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=False)
     generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=1024)
     thread = Thread(target=model.generate, kwargs=generation_kwargs)
     thread.start()