Llama-3.1-8B-Instruct

Running on Zero

vilarin commited on Jul 23

Commit

ce84a62

•

1 Parent(s): 3d7390f

Update app.py

Files changed (1) hide show

app.py CHANGED Viewed

@@ -69,7 +69,7 @@ def stream_chat(
     conversation.append({"role": "user", "content": message})
-    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt").to(model.device)
     streamer = TextIteratorStreamer(tokenizer, timeout=60.0, skip_prompt=True, skip_special_tokens=True)

     conversation.append({"role": "user", "content": message})
+    input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt=True, return_tensors="pt").to(model.device)
     streamer = TextIteratorStreamer(tokenizer, timeout=60.0, skip_prompt=True, skip_special_tokens=True)