Update app.py

app.py

@@ -5,31 +5,33 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 from peft import PeftModel
 from huggingface_hub import login
 
-# Authenticate with Hugging Face using secret HF_TOKEN
+# Login using HF token from secrets
 hf_token = os.environ.get("HF_TOKEN")
 if not hf_token:
-    raise RuntimeError("Missing HF_TOKEN in secrets. Please add it in your Space settings.")
-
+    raise RuntimeError("Missing HF_TOKEN in secrets.")
 login(token=hf_token)
 
-# Load base model and LoRA adapter
-base_model_id = "unsloth/gemma-2-9b"  # Or your base model
-lora_model_id = "Futuresony/future_12_10_2024"        # Your LoRA fine-tuned model
+# Base and LoRA model paths
+base_model_id = "unsloth/gemma-2-9b"
+lora_model_id = "Futuresony/future_12_10_2024"
 
-# Load tokenizer and model
+# Load tokenizer and base model
 tokenizer = AutoTokenizer.from_pretrained(base_model_id)
-base_model = AutoModelForCausalLM.from_pretrained(base_model_id, torch_dtype=torch.float16, device_map="auto")
-model = PeftModel.from_pretrained(base_model, lora_model_id)
+base_model = AutoModelForCausalLM.from_pretrained(
+    base_model_id,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
 
-# Ensure model is in evaluation mode
+# Load LoRA weights
+model = PeftModel.from_pretrained(base_model, lora_model_id)
 model.eval()
 
+# Chat function
 def generate_response(message, history, system_message, max_tokens, temperature, top_p):
     prompt = system_message + "\n\n"
-
     for user_input, bot_response in history:
         prompt += f"User: {user_input}\nAssistant: {bot_response}\n"
-
     prompt += f"User: {message}\nAssistant:"
 
     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
@@ -46,7 +48,7 @@ def generate_response(message, history, system_message, max_tokens, temperature,
     final_response = response.split("Assistant:")[-1].strip()
     return final_response
 
-# Gradio ChatInterface
+# Gradio interface
 demo = gr.ChatInterface(
     fn=generate_response,
     additional_inputs=[
@@ -55,9 +57,10 @@ demo = gr.ChatInterface(
         gr.Slider(0.1, 1.5, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p"),
     ],
-    title="LoRA AI Chat Assistant",
-    description="Chat with your fine-tuned model using LoRA adapter."
+    title="LoRA Chat Assistant (Gemma-2)",
+    description="Chat with your fine-tuned Gemma-2 LoRA model"
 )
 
 if __name__ == "__main__":
     demo.launch()
+