refactor: polish

.gitattributes

@@ -34,7 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 *.png filter=lfs diff=lfs merge=lfs -text
-*.md filter=lfs diff=lfs merge=lfs -text
-*.py filter=lfs diff=lfs merge=lfs -text
-*.txt filter=lfs diff=lfs merge=lfs -text
 *.csv filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,12 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c44d044e074ff03b22bd5bba6429e266c26f3dea6c4e3cdf3abd9f70a7938439
-size 406
+---
+title: Gradio Chatbot
+emoji: 💬
+colorFrom: yellow
+colorTo: purple
+sdk: gradio
+sdk_version: 5.0.1
+app_file: app.py
+pinned: false
+---
+
+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).

app.py

@@ -1,3 +1,64 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d6359e262aae36aec6373e8eb20498628b038369563ee54db01a9532f33db93d
-size 2356
+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("HuggingFaceH4/zephyr-7b-beta")
+
+
+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)",
+        ),
+    ],
+)
+
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -1,3 +1,3 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bfbc47c2455bc1a306bb2ee618c96b9bc1c325ff8314f0e49ee93454726553d9
-size 55
+huggingface_hub==0.25.2
+gradio==5.8.0
+matplotlib==3.9.3