Update app.py

app.py

@@ -19,7 +19,7 @@ st.markdown(f"*This chat uses the {REPO_NAME} model. Feel free to ask questions
 def load_model(repo_name):
     tokenizer = AutoTokenizer.from_pretrained(repo_name, trust_remote_code=True)
     generator_conf = GenerationConfig.from_pretrained(repo_name)
-    model = AutoModelForCausalLM.from_pretrained(repo_name, trust_remote_code=True)
+    model = AutoModelForCausalLM.from_pretrained(repo_name, trust_remote_code=True, torch_dtype=torch.bfloat16)
     return tokenizer, generator_conf, model
 
 tokenizer, generator_conf, model = load_model(REPO_NAME)