Update app.py

app.py

@@ -7,8 +7,8 @@ import spaces
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextIteratorStreamer
 
-subprocess.run('pip install -U transformers tokenizers', shell=True)
-subprocess.run('pip install -U flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
+subprocess.run('pip install --upgrade transformers tokenizers', shell=True)
+subprocess.run('pip install --upgrade flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
 MODEL_ID = "AtAndDev/marco-qwq-7B"
 CHAT_TEMPLATE = "ChatML"
@@ -110,7 +110,7 @@ quantization_config = BitsAndBytesConfig(
     load_in_4bit=True,
     bnb_4bit_compute_dtype=torch.bfloat16
 )
-tokenizer = AutoTokenizer.from_pretrained('AtAndDev/marco-qwq-7B')
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
     device_map="auto",