Update space

app.py

@@ -1,42 +1,64 @@
-import gradio as gr # type: ignore
-from transformers import AutoTokenizer, AutoModelForCausalLM
-
-# Load PhoGPT-4B-Chat model and tokenizer
-tokenizer = AutoTokenizer.from_pretrained("vinai/PhoGPT-4B-Chat", trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained("vinai/PhoGPT-4B-Chat", trust_remote_code=True)
-
-# Response function for chat interface
-def respond(message, history, system_message, max_tokens, temperature, top_p):
-    prompt = system_message + "\n"
-    for user_msg, bot_msg in history:
-        prompt += f"User: {user_msg}\nBot: {bot_msg}\n"
-    prompt += f"User: {message}\nBot:"
-
-    inputs = tokenizer(prompt, return_tensors="pt")
-    outputs = model.generate(
-        **inputs,
-        max_new_tokens=max_tokens,
+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,
-        do_sample=True,
-        pad_token_id=tokenizer.eos_token_id
-    )
-    full = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    answer = full.replace(prompt, "").strip()
-    if not answer:
-        answer = "[Không thể tạo câu trả lời, vui lòng thử lại!]"
-    yield answer
-
-# Gradio interface
+    ):
+        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="Bạn là một chatbot người Việt thân thiện.", label="System message"),
-        gr.Slider(1, 2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(0.1, 4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
+        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()