shirish
@shiri_shh
Generalist | AI | Tech | Startups ▪︎ Locked in
Joined December 2014
1.5K Following 45.7K Followers
btw fine-tuning open-source models at 2x the speed is easy now. you just need:
- your favorite base model (Llama, Qwen, Mistral)
- a single YAML config file
- Halo from @whitecircle
up to 2.8x faster throughput, lower peak VRAM, and 0 checkpoint conversion scripts
Show more
Introducing Halo, the best framework for post-training of open-source models.
Halo delivers up to 2.8x the throughput of stock TRL with less peak memory, while models stay in their native HuggingFace format.
Star us on GitHub:
Show more
