test

app.py

@@ -6,8 +6,8 @@ app = FastAPI()
 
 hf_token = os.getenv('HUGGINGFACE_HUB_TOKEN')
 
-model = AutoModelForCausalLM.from_pretrained("mistral/Mistral-7B-Instruct-v0.3", use_auth_token=hf_token)
-tokenizer = AutoTokenizer.from_pretrained("mistral/Mistral-7B-Instruct-v0.3")
+model = AutoModelForCausalLM.from_pretrained("mistral/Mistral-7B-v0.3", use_auth_token=hf_token)
+tokenizer = AutoTokenizer.from_pretrained("mistral/Mistral-7B-v0.3")
 
 @app.post("/inference")
 async def inference(prompt: str):