Changed Model

app.py

@@ -1,12 +1,13 @@
 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")
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
+# Load DialoGPT model and tokenizer
+model_name = "microsoft/DialoGPT-large"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
+# Respond function for Gradio interface
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -15,34 +16,28 @@ def respond(
     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,
+    # Format the chat history for the DialoGPT model
+    full_conversation = ""
+    for user_msg, bot_msg in history:
+        if user_msg:
+            full_conversation += f"User: {user_msg}\n"
+        if bot_msg:
+            full_conversation += f"DialoGPT: {bot_msg}\n"
+    full_conversation += f"User: {message}\nDialoGPT:"
+
+    # Tokenize input and generate response
+    inputs = tokenizer.encode(full_conversation, return_tensors="pt")
+    outputs = model.generate(
+        inputs,
+        max_length=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+        pad_token_id=tokenizer.eos_token_id,
+    )
+    response = tokenizer.decode(outputs[:, inputs.shape[-1] :][0], skip_special_tokens=True)
+    return response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Gradio Chat Interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -59,6 +54,7 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    # Launch the Gradio app with API enabled
+    demo.launch(enable_api=True)
+