debug

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

@@ -1,7 +1,6 @@
 from flask import Flask, request, jsonify
 from huggingface_hub import login
 from transformers import AutoModelForCausalLM, AutoTokenizer
-from threading import Thread
 import spaces
 import torch
 import os
@@ -35,8 +34,6 @@ def chat_completion():
     try:
         input_ids = tokenizer.apply_chat_template(user_input, tokenize=False, add_generation_prompt=True)
         inputs = tokenizer(input_ids, return_tensors="pt").to(0)
-        
-        streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
 
         generate_kwargs = dict(
             inputs,