yes

app.py

@@ -11,17 +11,17 @@ login(token=token)
 
 # Load your model and tokenizer
 
-# model, tokenizer = load("Rafii/f1llama")
+model, tokenizer = load("Rafii/f1llama")
 
-prompt="hello world"
+prompt="hello"
 
-# if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
-#     messages = [{"role": "user", "content": prompt}]
-#     prompt = tokenizer.apply_chat_template(
-#         messages, tokenize=False, add_generation_prompt=True
-#     )
+if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
 
-# # response = generate(model, tokenizer, prompt=prompt, verbose=True)
+# response = generate(model, tokenizer, prompt=prompt, verbose=True)
 
 st.title("Your F1 Bro")
 
@@ -32,6 +32,6 @@ if st.button("Submit"):
     # Tokenize input and make predictions
     # inputs = tokenizer(user_input, return_tensors="pt")
     # outputs = model(**inputs)
-    # response = generate(model, tokenizer, prompt=user_input, verbose=True)
+    response = generate(model, tokenizer, prompt=user_input, verbose=True)
 
-    st.write("Hello World!")
+    st.write(response)