Update app.py

app.py

@@ -1,79 +1,53 @@
 import gradio as gr
-import psycopg2
-from database import db_connection
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-"""
-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("WhiteRabbitNeo/WhiteRabbitNeo-13B-v1")
+# Load the model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("WhiteRabbitNeo/WhiteRabbitNeo-13B-v1", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("WhiteRabbitNeo/WhiteRabbitNeo-13B-v1", trust_remote_code=True)
 
-CREATOR_NAME = "Ridimz"  # Define your creator name here
-
-def fetch_system_message():
-    conn = db_connection()
-    cursor = conn.cursor()
-    cursor.execute("SELECT message FROM system_messages WHERE name = 'MicroAI'")
-    result = cursor.fetchone()
-    cursor.close()
-    conn.close()
+# Define a function to generate text with a system message
+def generate_response(prompt, system_message, token):
+    # Combine system message and user prompt
+    full_prompt = f"{system_message}\n\n{prompt}"
     
-    if result:
-        return result[0]  # Return the message associated with 'MicroAI'
-    else:
-        return f"You are Micro AI, created by {CREATOR_NAME}. Follow the instructions precisely."
-
-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
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value=fetch_system_message(), label="System message"),  # Call the function to fetch 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)",
-        ),
+    # Tokenize input
+    inputs = tokenizer(full_prompt, return_tensors="pt", truncation=True)
+    
+    # Generate a response
+    outputs = model.generate(
+        inputs["input_ids"],
+        max_length=300,
+        do_sample=True,
+        temperature=0.7,
+        top_k=50,
+        pad_token_id=tokenizer.eos_token_id  # To prevent padding issues
+    )
+    
+    # Decode the output text
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    
+    # If a token is provided, add it to the response
+    if token:
+        response += f"\n\nToken Used: {token}"
+    
+    return response
+
+# Create a Gradio interface
+interface = gr.Interface(
+    fn=generate_response,
+    inputs=[
+        gr.Textbox(lines=5, label="Prompt", placeholder="Type your prompt here..."),
+        gr.Textbox(lines=1, label="System Message", placeholder="System message (optional)"),
+        gr.Textbox(lines=1, label="Token", placeholder="Enter token (optional)"),
     ],
+    outputs=gr.Textbox(label="Generated Response"),
+    title="WhiteRabbitNeo Enhanced Model",
+    description=(
+        "This app uses the WhiteRabbitNeo-13B-v1 model to generate text responses. "
+        "You can provide a system message, a prompt, and optionally include a token for custom usage."
+    ),
 )
 
+# Launch the app
 if __name__ == "__main__":
-    demo.launch()
+    interface.launch()