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.
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.
273 points by jph00 | 80 comments
330 points by tanelpoder | 305 comments
Answer.AI blog post examining PyPI package creation and update data to look for evidence that AI coding tools have increased software output.
235 points by swyx | 130 comments