Update app.py

app.py

@@ -101,7 +101,7 @@ def bot_streaming(message, history):
     stop_str = '<|im_end|>'
     keywords = [stop_str]
     stopping_criteria = KeywordsStoppingCriteria(keywords, tokenizer, input_ids)
-    streamer = TextIteratorStreamer(tokenizer, skip_prompt=False, skip_special_tokens=True)
+    streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
     
     image_tensor = model.process_images([image], model.config).to(dtype=model.dtype)
     generation_kwargs = dict(input_ids=input_ids.to('cuda'), images=image_tensor.to('cuda'), streamer=streamer, max_new_tokens=100, stopping_criteria=[stopping_criteria])
@@ -115,7 +115,7 @@ def bot_streaming(message, history):
       
       buffer += new_text
       
-      generated_text_without_prompt = buffer[len(text_prompt):]
+      generated_text_without_prompt = buffer[:]
       time.sleep(0.04)
       yield generated_text_without_prompt