Update app.py

app.py

@@ -24,7 +24,7 @@ class MessageRequest(BaseModel):
     message: str
     language: str
 
-repo_id = "meta-llama/Meta-Llama-3-8B-Instruct"
+repo_id = "meta-llama/Meta-Llama-3-8B"
 llm_client = InferenceClient(
     model=repo_id,
     token=os.getenv("HF_TOKEN"),
@@ -60,8 +60,8 @@ templates = Jinja2Templates(directory="static")
 
 # Configure Llama index settings
 Settings.llm = HuggingFaceInferenceAPI(
-    model_name="meta-llama/Meta-Llama-3-8B-Instruct",
-    tokenizer_name="meta-llama/Meta-Llama-3-8B-Instruct",
+    model_name="meta-llama/Meta-Llama-3-8B",
+    tokenizer_name="meta-llama/Meta-Llama-3-8B",
     context_window=3000,
     token=os.getenv("HF_TOKEN"),
     max_new_tokens=512,