Update app.py

app.py

@@ -1,49 +1,60 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
-"""
-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 your model and tokenizer from Hugging Face
+model_name = 'redael/model_udc'
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+# Function to generate response
+def generate_response(message, history, system_message, max_tokens, temperature, top_p):
+    # Prepare the conversation history
     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]})
-
+    
+    for user_msg, bot_msg in history:
+        if user_msg:
+            messages.append({"role": "user", "content": user_msg})
+        if bot_msg:
+            messages.append({"role": "assistant", "content": bot_msg})
+    
     messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    
+    # Tokenize and prepare the input
+    prompt = "\n".join([f"{msg['role'].capitalize()}: {msg['content']}" for msg in messages])
+    inputs = tokenizer(prompt, return_tensors='pt', padding=True, truncation=True, max_length=512).to(device)
+    
+    # Generate the response
+    outputs = model.generate(
+        inputs['input_ids'],
+        max_length=max_tokens,
+        num_return_sequences=1,
+        pad_token_id=tokenizer.eos_token_id,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+        early_stopping=True,
+        do_sample=True  # Enable sampling
+    )
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    
+    # Clean up the response
+    response = response.split("Assistant:")[-1].strip()
+    response_lines = response.split('\n')
+    clean_response = []
+    for line in response_lines:
+        if "User:" not in line and "Assistant:" not in line:
+            clean_response.append(line)
+    response = ' '.join(clean_response)
+    
+    return [(message, response)]
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Create the Gradio chat interface
 demo = gr.ChatInterface(
-    respond,
+    fn=generate_response,
     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"),
@@ -56,8 +67,9 @@ demo = gr.ChatInterface(
             label="Top-p (nucleus sampling)",
         ),
     ],
+    title="Chatbot",
+    description="Ask anything to the chatbot."
 )
 
-
 if __name__ == "__main__":
     demo.launch()