Upload folder using huggingface_hub

README.md

@@ -6,6 +6,7 @@ colorTo: indigo
 sdk: gradio
 sdk_version: 6.11.0
 app_file: app.py
+python_version: "3.12"
 pinned: false
 license: mit
 ---

app.py

@@ -194,9 +194,7 @@ def generate_spec(
         {"role": "user", "content": user_content},
     ]
 
-    input_text = tokenizer.apply_chat_template(
-        messages, tokenize=False, add_generation_prompt=True
-    )
+    input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
     inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
     input_len = inputs["input_ids"].shape[-1]
 
@@ -244,7 +242,13 @@ def create_app():
             with gr.Column(scale=1):
                 spec_output = gr.Markdown(label="Generated Specification")
 
+        gr.Markdown("*Model loads on first generation (~30s). Subsequent calls are fast.*")
+
+        loading_msg = "*Generating specification... (loading model if first run)*"
         generate_btn.click(
+            fn=lambda: gr.update(value=loading_msg),
+            outputs=spec_output,
+        ).then(
             fn=generate_spec,
             inputs=[code_input, temperature, top_p, max_tokens, use_rag],
             outputs=spec_output,