Upload 2 files

README.md

@@ -1,14 +1,12 @@
 ---
-title: Llama-160M-Chat
-emoji: 💬
-colorFrom: yellow
-colorTo: purple
+title: Meta Llama Llama 3.2 1B Instruct
+emoji: 📊
+colorFrom: blue
+colorTo: blue
 sdk: gradio
-sdk_version: 5.9.1
+sdk_version: 5.3.0
 app_file: app.py
 pinned: false
-license: wtfpl
-short_description: Does it speak?
 ---
 
-An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,63 +1,3 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
 
-"""
-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("huihui-ai/Llama-3.2-1B-Instruct-abliterated")
-
-
-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 an exceptional AI assistant.", label="System message"),
-        gr.Slider(minimum=1, maximum=512, value=100, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=1.0, value=0.5, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.80,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+gr.load("models/meta-llama/Llama-3.2-1B-Instruct").launch()