Nikita Sushko
chameleon-lizard
AI & ML interests
NLP, Multilingual Models, Multiagent Systems
Recent Activity
upvoted a paper 12 days ago
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines? upvoted an article 25 days ago
CRAFT: Continuous Reasoning and Agentic Feedback Tuning upvoted a paper 28 days ago
Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation Organizations
[MODELS] Discussion
❤️ 👍 38
800
#372 opened about 2 years ago
by
victor
eos_token should be <|eot_id|>
5
#1 opened almost 2 years ago
by
AUTOMATIC