dafeadfe

app.py

@@ -64,17 +64,17 @@ def train_ui_tars(file):
         trainer.train()
        
         # Step 5: Save the model
-        model.save_pretrained("./fine_tuned_llama2")
-        tokenizer.save_pretrained("./fine_tuned_llama2")
+        model.save_pretrained("train_llama.py")
+        tokenizer.save_pretrained("./train_llama.py")
        
-        return "Training completed successfully! Model saved to ./fine_tuned_llama2"
+        return "Training completed successfully! Model saved to ./train_llama.py"
    
     except Exception as e:
         return f"Error: {str(e)}"
 
 # Gradio UI
 with gr.Blocks(title="Model Fine-Tuning Interface") as demo:
-    gr.Markdown("# OPT-350M Fine-Tuning UI")
+    gr.Markdown("train_llama.py")
     gr.Markdown("Upload a JSON file with 'input' and 'output' pairs to fine-tune the model on your fraud dataset.")
    
     file_input = gr.File(label="Upload Fraud Dataset (JSON)")

requirements.txt

@@ -1,4 +1,7 @@
 torch
 transformers
 datasets
-gradio
+gradio
+peft
+accelerate
+bitsandbytes