arxiv:2602.06717
Alexey Gorbatovski
Myashka
AI & ML interests
NLP Alignment
Recent Activity
liked
a Space 5 days ago
t-tech/manifolds upvoted a paper 6 days ago
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines? authored
a paper
15 days ago
F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare Organizations
None yet
models 37
Myashka/Qwen2.5-7B-UltraChat200K_EMA_SFT-Lr_3e_6-Alpha_0.01
Text Generation • 8B • Updated
• 2
Myashka/Qwen2.5-7B-UltraChat200K_SFT-Lr_3e_6
8B • Updated
Myashka/gpt-imdb-kto-beta_0.1
Text Generation • 0.1B • Updated
• 2
Myashka/gpt-imdb-hinge-beta_0.1
Text Generation • 0.1B • Updated
• 6
Myashka/gpt-imdb-dpo_annealing
Text Generation • 0.1B • Updated
• 1
Myashka/gpt-imdb-alpha_0.3-beta_0.1
Text Generation • 0.1B • Updated
• 1
Myashka/gpt-imdb-ipo-beta_0.3
Text Generation • 0.1B • Updated
• 1
Myashka/gpt-imdb-ipo-beta_0.1
Text Generation • 0.1B • Updated
Myashka/gpt-imdb-ipo_annealing
Text Generation • 0.1B • Updated
• 1
Myashka/gpt-imdb-alpha_0.5-beta_0.1
Text Generation • 0.1B • Updated
• 1
datasets 11
Myashka/CryptoNews_50_50
Viewer
• Updated
• 1.15k • 32
Myashka/CryptoNews
Viewer
• Updated
• 1.15k • 5
Myashka/gpt2-imdb-constractive
Viewer
• Updated
• 59.1k • 4
Myashka/SO_Python_basics_QA_human_pref
Viewer
• Updated
• 185k • 26
Myashka/SO-Python_basics_QA-filtered-2023-T5_paraphrased-tanh_score
Viewer
• Updated
• 117k • 8
Myashka/SO_Python_basics_QA_human_preferences_no_gen
Viewer
• Updated
• 6.17k • 29
Myashka/SO-Python_basics_QA-filtered-2023-tanh_score
Viewer
• Updated
• 30k • 18
Myashka/SO-Python_QA-filtered-2023-no_code-tanh_score
Viewer
• Updated
• 66.1k • 10 • 2
Myashka/SO-Python_QA-filtered-2023-tanh_score
Viewer
• Updated
• 69.5k • 14
Myashka/SO-Python_QA-filtered-2023-tanh_score-after_2023_02
Viewer
• Updated
• 1.06k • 12 • 1