Update app.py

app.py

@@ -1,38 +1,64 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-from transformers import AutoTokenizer
-
-# Set the model name and initialize the InferenceClient and tokenizer
-model_name = "PierreJousselin/lora_model"  # Model name on Hugging Face
-client = InferenceClient(model_name)
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-
-# Define the function to interact with the model
-def chat_with_model(input_text, max_length=100):
-    # Tokenize the input text
-    inputs = tokenizer(input_text, return_tensors="pt", truncation=True, padding=True, max_length=512)
-    
-    # Generate text using the Hugging Face Inference API
-    result = client.text_generation(
-        inputs=inputs["input_ids"].tolist(),  # Send tokenized input
-        parameters={"max_length": max_length + len(inputs["input_ids"][0]), "temperature": 1.0}
-    )
-    
-    # Decode the generated text back to a readable format
-    response = tokenizer.decode(result[0]["generated_text"], skip_special_tokens=True)
-    
-    return response
-
-# Set up the Gradio interface
-interface = gr.Interface(
-    fn=chat_with_model,
-    inputs=[gr.Textbox(lines=5, placeholder="Enter your text here...", label="Input Text"),
-            gr.Slider(minimum=50, maximum=500, step=10, value=100, label="Max Length")],
-    outputs=gr.Textbox(lines=5, label="Response"),
-    title="Conversational Model",
-    description="A conversational chatbot powered by a Hugging Face model using the 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("PierreJousselin/lora_model")
+
+
+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)",
+        ),
+    ],
 )
 
-# Launch the Gradio app
+
 if __name__ == "__main__":
-    interface.launch()
+    demo.launch()