Myashka/125M_GPTneo-ppo_tuned-max_reward
Text Generation • Updated
Alexey Gorbatovski
Myashka
AI & ML interests
NLP Alignment
Recent Activity
liked
a Space 22 days ago
t-tech/manifolds upvoted a paper 23 days ago
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines? authored
a paper
about 1 month ago
F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare Organizations
None yet
Myashka/125M_GPTneo-ppo_tuned-last_epoch
Text Generation • Updated
Myashka/125M_GPTneo_reward_gen
Text Classification • Updated
• 4
Myashka/125M_GPTneo_reward_base
Text Classification • Updated
• 1
Myashka/125M_GPTneo_sft_tuned
Text Generation • Updated
• 2
Myashka/GPT_neo_python_QA
Updated
Myashka/emotion-hi
Updated