Update app.py

app.py

@@ -1,47 +1,64 @@
 import gradio as gr
-from transformers import pipeline, AutoTokenizer, TextStreamer
-
-class CustomTextStreamer(TextStreamer):
-    def __init__(self, tokenizer, decode_kwargs=None):
-        super().__init__(tokenizer, decode_kwargs=decode_kwargs)
-        self.output_text = ""
-
-    def on_token(self, token_id):
-        token = self.tokenizer.decode([token_id], **self.decode_kwargs)
-        self.output_text += token
-        print(token, end='', flush=True)
-
-def load_model():
-    # Create tokenizer and model
-    tokenizer = AutoTokenizer.from_pretrained("cognitivecomputations/dolphin-2_6-phi-2", trust_remote_code=True)
-    pipe = pipeline(
-        "text-generation", 
-        model="cognitivecomputations/dolphin-2_6-phi-2", 
-        tokenizer=tokenizer,
-        device=0,
-        trust_remote_code=True
-    )
-    return pipe, tokenizer
-
-def chat(message, history):
-    pipe, tokenizer = load_model()
-    streamer = CustomTextStreamer(tokenizer)
-    
-    messages = [
-        {"role": "system", "content": "You are a helpful AI assistant."},
-        {"role": "user", "content": message},
-    ]
-    
-    # Generate response
-    response = pipe(messages, max_length=540, streamer=streamer)
-    return streamer.output_text
-
-# Create Gradio interface
+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(
-    fn=chat,
-    title="Dolphin-2.6-phi-2 Chat",
-    description="Chat with the Dolphin-2.6-phi-2 model"
+    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(share=True)
+    demo.launch()