Update llava_llama3/serve/cli.py

llava_llama3/serve/cli.py

@@ -26,7 +26,7 @@ def load_image(image_file):
     return image
 
 
-def chat_llava(args, image_file, text, tokenizer, model, image_processor, context_len):
+def chat_llava(args, image_file, text, tokenizer, model, streamer, image_processor, context_len):
     # Model
     disable_torch_init()
 
@@ -63,7 +63,7 @@ def chat_llava(args, image_file, text, tokenizer, model, image_processor, contex
     input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).to(model.device)
     stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2
     keywords = [stop_str]
-    streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+    # streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
 
     with torch.inference_mode():
         output_ids = model.generate(