debug

data/models/llama3-1-70b.py

@@ -41,7 +41,7 @@ def chat_completion():
                     eos_token_id=[128001, 128009]
                 ).to("cuda")
         
-        outputs = model.generate(**inputs, do_sample=True, max_new_tokens=max_tokens,temperature=temperature,top_p=top_p,token=True).to("cuda")
+        outputs = model.generate(**inputs, do_sample=True, max_new_tokens=max_tokens,temperature=temperature,top_p=top_p,token=api_key).to("cuda")
 
         return jsonify({"status": "success", "output": tokenizer.batch_decode(outputs[:, inputs['input_ids'].shape[1]:], skip_special_tokens=True)[0]})
     except Exception as e: