Update app.py

app.py

@@ -10,7 +10,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
 
 subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
-MODEL_ID = "OEvortex/HelpingAI-9B"
+MODEL_ID = "OEvortex/HelpingAI-3B-v3"
 CHAT_TEMPLATE = os.environ.get("CHAT_TEMPLATE")
 MODEL_NAME = MODEL_ID.split("/")[-1]
 CONTEXT_LENGTH = int(os.environ.get("CONTEXT_LENGTH"))