Python

llm-finetune-lab

LoRA and PEFT instruction fine-tuning with prompt masking. TinyLlama by default, a distilgpt2 CPU smoke test, and a generate script to try the trained adapter.

View on GitHub

CI passing · Python

llm-finetune-lab

Highlights

LoRA / PEFT supervised fine-tuning
Prompt masking so loss lands on the response
TinyLlama default, distilgpt2 CPU smoke test
generate.py to try the adapter

Want the code?

View on GitHub