AI Safety Research

AISafety

AI & ML interests

LLMs, planning, EA

Recent Activity

Organizations

None yet

AISafety's activity

New activity in dagim/urban-dictionary-embeddings 6 days ago

size flag is off

#1 opened 6 days ago by AISafety
Reacted to hbseong's post with πŸ”₯ 7 days ago
view post
Post
903
🚨πŸ”₯ New Release Alert! πŸ”₯🚨

Introducing the 435M model that outperforms Llama-Guard-3-8B while slashing 75% of the computation cost! πŸ’»πŸ’₯
πŸ‘‰ Check it out: hbseong/HarmAug-Guard (Yes, INFERENCE CODE INCLUDED! πŸ’‘)

More details in our paper: https://arxiv.org/abs/2410.01524 πŸ“œ

#HarmAug #LLM # Safety #EfficiencyBoost #Research #AI #MachineLearning
  • 1 reply
Β·
upvoted an article 30 days ago
view article
Article

Decoding Strategies in Large Language Models

By mlabonne β€’
β€’ 38
liked a Space about 2 months ago