Update app.py

app.py

@@ -1,64 +1,70 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-"""
-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")
+# Load model and tokenizer
+model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-small")
+tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-small")
 
+def chat_response(message, history):
+    try:
+        # Build conversation history string
+        chat_history_ids = None
+        for human_msg, bot_msg in history:
+            # Encode user message
+            user_input_ids = tokenizer.encode(
+                human_msg + tokenizer.eos_token,
+                return_tensors='pt'
+            )
+            # Encode bot response
+            bot_output_ids = tokenizer.encode(
+                bot_msg + tokenizer.eos_token,
+                return_tensors='pt'
+            )
+            # Build full conversation
+            if chat_history_ids is None:
+                chat_history_ids = torch.cat([user_input_ids, bot_output_ids], dim=-1)
+            else:
+                chat_history_ids = torch.cat([chat_history_ids, user_input_ids, bot_output_ids], dim=-1)
+        
+        # Add new user message
+        new_user_input_ids = tokenizer.encode(
+            message + tokenizer.eos_token,
+            return_tensors='pt'
+        )
+        
+        # Generate response
+        chat_history_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if chat_history_ids is not None else new_user_input_ids
+        
+        # Generate bot response
+        bot_output_ids = model.generate(
+            chat_history_ids,
+            max_length=1000,
+            pad_token_id=tokenizer.eos_token_id,
+            no_repeat_ngram_size=3,
+            do_sample=True,
+            top_k=100,
+            top_p=0.7,
+            temperature=0.8
+        )
+        
+        # Extract only the bot's response (remove history)
+        response = tokenizer.decode(
+            bot_output_ids[:, chat_history_ids.shape[-1]:][0],
+            skip_special_tokens=True
+        )
+        
+        return response
+    
+    except Exception as e:
+        return f"Error: {str(e)}"
 
-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
-"""
+# Create chat interface
 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)",
-        ),
-    ],
+    chat_response,
+    title="DialoGPT Chatbot",
+    examples=["Hello!", "What's AI?", "Tell me a joke"],
+    type="messages"
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()