Update app.py

app.py

@@ -11,7 +11,7 @@ def load_model(model_path):
     base_model = AutoModelForCausalLM.from_pretrained(
         config.base_model_name_or_path,
         trust_remote_code=True,
-        # token=os.environ["HF_TOKEN"],
+        token=os.environ["HF_TOKEN"],
     )
 
     base_model.config.use_cache = False
@@ -58,19 +58,21 @@ def generate_text(prompt):
 device = 'cuda' if torch.cuda.is_available() else 'cpu'
 model, tokenizer = load_model(os.path.join(os.getcwd(), "weights"))
 
-
 iface = gr.Interface(
     fn=generate_text,
     inputs=[
-        gr.Textbox(label="Prompt", placeholder="Enter your prompt here..."),
-    ],
+        gr.Textbox(label="Prompt", 
+                   placeholder="Enter your prompt here...",
+                   lines=5
+                  ),
+        ],
     outputs=gr.Textbox(label="Generated Text"),
     title="LLaMA-3.2-3B-Instruct-QLoRA",
-    description="-3.2-3B-Instruct Finetuned using QLoRA on OpenAssistant/oasst1",
+    description="LLaMA-3.2-3B-Instruct Finetuned using QLoRA on OpenAssistant/oasst1",
     examples=[
         ["can you describe winter?"],
         ["How about we play a fun game?"],
-    ],
+    ]
 )