Fine tune a 70B language model at home(answer.ai)
821 points by jph00 | 197 comments
Answer.AI blog post announcing an open source system combining FSDP and QLoRA to train a 70B language model on two 24GB consumer GPUs.
#qlora on Hacker News
2 stories tagged qlora, newest first.
Show HN: 80% faster, 50% less memory, 0% loss of accuracy Llama finetuning(github.com)
336 points by danielhanchen | 107 comments
GitHub repository for Unsloth, an open-source library for faster, lower-memory QLoRA/LoRA finetuning of Llama models using Triton kernels.