Update app.py

app.py

@@ -1,11 +1,10 @@
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
 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")
 
+# Load DialoGPT model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
+model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
 
 def respond(
     message,
@@ -15,29 +14,37 @@ 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]})
+    # Prepare the context from history
+    chat_history = ""
+    for user_input, bot_response in history:
+        if user_input:
+            chat_history += f"User: {user_input}\n"
+        if bot_response:
+            chat_history += f"Bot: {bot_response}\n"
 
-    messages.append({"role": "user", "content": message})
+    # Append the new user message
+    chat_history += f"User: {message}\n"
 
-    response = ""
+    # Tokenize the input
+    input_ids = tokenizer.encode(chat_history, return_tensors="pt")
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    # Generate response
+    output_ids = model.generate(
+        input_ids,
+        max_length=max_tokens + len(input_ids[0]),
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        pad_token_id=tokenizer.eos_token_id,
+    )
 
-        response += token
-        yield response
+    # Decode the output and get the response
+    output = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+
+    # Extract the bot's response
+    bot_response = output.split("User:")[-1].split("Bot:")[-1].strip()
+    history.append((message, bot_response))  # Update history
+
+    yield bot_response
 
 
 """
@@ -59,6 +66,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()