How I Doubled Chatbot Performance with LLM Fine-Tuning (FT)

I needed to build a customer service chatbot for my company, so I tried fine-tuning with LoRA.

1. Base model: Llama 3.1 8B (good Korean support)

2. Dataset: Refined 50,000 in-house CS logs and converted them into instruction format

3. Training: Ran QLoRA on 16GB VRAM (4-bit quantization)

4. Result: Accuracy increased from 68% to 89%, and hallucinations decreased

The most effective addition was including data on 'responses to incorrect questions.'

If anyone has FT experience, please share tips on data preprocessing.

by 프롬프트장인174

5 answers

Agreed, LoRA is really good lol. I also FT'd with 8B and performance definitely improved.

by 클라우드러버384 · ▲0

Well, I think claiming double the accuracy is a bit exaggerated... I'm curious about the before-and-after evaluation criteria.

by 호기심천국21 · ▲0

Wow, from 68 to 89 is almost a 30 percentage point increase—that's impressive. For me, the toughest part of data cleaning was removing duplicate inquiries. How do you handle it?

by AI덕후148 · ▲0

Oh, adding data to handle incorrect questions is the key point. I haven't tried that far yet, but I should give it a shot.

by 데이터덕후610 · ▲0

QLoRA only uses 16GB? That's less than I expected. But doesn't 4-bit quantization cause some performance loss? In my experience, 8-bit was more stable.

by 클라우드러버732 · ▲0