Dcas89 PRO
Dcas89
ยท
AI & ML interests
None yet
Recent Activity
reacted
to
sergiopaniego's
post
with ๐ฅ
7 days ago
This summer TRL leveled up for multimodal alignment ๐
โ
New VLM alignment methods (MPO, GRPO, GSPO)
โ
Extended RLOO & Online DPO for VLMs
โ
Native SFT support
โ
Ready-to-use training scripts
๐ https://huggingface.co/blog/trl-vlm-alignment
reacted
to
sergiopaniego's
post
with ๐ค
about 2 months ago
So you can now SFT a model with hf jobs + TRL in ONE command lol ๐๏ธ๐จ
Without worrying about infrastructure since it runs entirely on HF!
docs: https://huggingface.co/docs/huggingface_hub/main/en/guides/jobs
blog: https://huggingface.co/blog/hf-cli
Organizations
None yet