using gpt 3.5

app.py

@@ -1,33 +1,58 @@
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
-import torch
+from huggingface_hub import InferenceClient
 
-# Load the model and tokenizer
-model_name = "facebook/opt-1.3b"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
+# Example of a freely accessible model
+client = InferenceClient("gpt-3.5-turbo")
 
-def respond(message, history):
-    # Tokenize input
-    inputs = tokenizer.encode(message + tokenizer.eos_token, return_tensors="pt")
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
 
-    # Generate response
-    outputs = model.generate(inputs, max_length=500, pad_token_id=tokenizer.eos_token_id)
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
 
-    # Append user input and response to history
-    history.append((message, response))
-    return history
+    messages.append({"role": "user", "content": message})
 
-# Gradio interface
+    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(label="User Input")
+        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)",
+        ),
     ],
-    title="OPT-1.3B Chatbot",
-    description="A chatbot powered by the OPT-1.3B model from Facebook.",
-    theme="compact",
 )
 
 if __name__ == "__main__":