Llama-3.2-1B-Instruct

Running on Zero

vilarin commited on Jul 3

Commit

75ba600

•

1 Parent(s): 9074f74

Update app.py

Files changed (1) hide show

app.py CHANGED Viewed

@@ -46,7 +46,7 @@ model = model.eval()
 def stream_chat(message: str, history: list, temperature: float, max_new_tokens: int, top_p: float, top_k: int, penalty: float):
     print(history)
-    resp, hist = model.stream_chat(
         tokenizer,
         query = message,
         history = history,
@@ -56,7 +56,7 @@ def stream_chat(message: str, history: list, temperature: float, max_new_tokens:
         top_k = top_k,
         temperature = temperature,
     )
     yield resp

 def stream_chat(message: str, history: list, temperature: float, max_new_tokens: int, top_p: float, top_k: int, penalty: float):
     print(history)
+    resp = model.stream_chat(
         tokenizer,
         query = message,
         history = history,
         top_k = top_k,
         temperature = temperature,
     )
+    print(resp)
     yield resp