Upload model.py

model.py

@@ -70,15 +70,7 @@ def run(message: str,
     )
     t = Thread(target=model.generate, kwargs=generate_kwargs)
     t.start()
-with torch.no_grad():
-    token_ids = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
-    output_ids = model.generate(
-        token_ids.to(model.device),
-        max_new_tokens=256,
-        pad_token_id=tokenizer.pad_token_id,
-        eos_token_id=tokenizer.eos_token_id,
-    )
-output = tokenizer.decode(output_ids.tolist()[0][token_ids.size(1) :], skip_special_tokens=True)
+
     outputs = []
     for text in streamer:
         outputs.append(text)