Update app.py

app.py

@@ -1,66 +1,10 @@
+
 import gradio as gr
-from huggingface_hub import InferenceClient
 import spaces
+import transformers_gradio
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("MakiAi/Llama-3.2-3B-Instruct-bnb-4bit-OKU_wiki_llama3.1_8b_inst_Reflexive_chunk200_overlap700-10epochs")
-
-
-@spaces.GPU
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
+demo = gr.load(name="MakiAi/Llama-3.2-3B-Instruct-bnb-4bit-OKU_wiki_llama3.1_8b_inst_Reflexive_chunk200_overlap700-10epochs", src=transformers_gradio.registry)
+demo.fn = spaces.GPU()(demo.fn)
 
 if __name__ == "__main__":
-    demo.launch(ssr_mode=False)
+    demo.launch()