Spaces:

huggingface-projects
/

llama-2-7b-chat

Running on Zero

hysts HF Staff commited on Jul 20, 2023

Commit

dc8c56e

1 Parent(s): 0095fd4

Update

Files changed (1) hide show

model.py CHANGED Viewed

@@ -34,7 +34,7 @@ def run(message: str,
         top_p: float = 0.95,
         top_k: int = 50) -> Iterator[str]:
     prompt = get_prompt(message, chat_history, system_prompt)
-    inputs = tokenizer([prompt], return_tensors='pt').to("cuda")
     streamer = TextIteratorStreamer(tokenizer,
                                     timeout=10.,

         top_p: float = 0.95,
         top_k: int = 50) -> Iterator[str]:
     prompt = get_prompt(message, chat_history, system_prompt)
+    inputs = tokenizer([prompt], return_tensors='pt').to('cuda')
     streamer = TextIteratorStreamer(tokenizer,
                                     timeout=10.,