Spaces:

choltha
/

free-CPU-inference-for-testing

Paused

Christoph Holthaus commited on Dec 11, 2023

Commit

878d5c0

1 Parent(s): e80da7c

dev - magic

Files changed (1) hide show

app.py CHANGED Viewed

@@ -93,7 +93,7 @@ def generate(
         gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
     input_ids = input_ids.to(model.device)
-    streamer= Llama()
     streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         {"input_ids": input_ids},

         gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
     input_ids = input_ids.to(model.device)
+    llm.generate('test')
     streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         {"input_ids": input_ids},