Configuration error
Local Perplexity
🚀
Avi Trost
atrost
AI & ML interests
None yet
Recent Activity
upvoted a paper about 17 hours ago
When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning? updated a model about 21 hours ago
atrost/q1_dp0_loss_kl_pcgrad_b0150_savefix_2xh100 published a model about 21 hours ago
atrost/q1_dp0_loss_kl_pcgrad_b0150_savefix_2xh100Organizations
models 131
atrost/q1_dp0_loss_kl_pcgrad_b0150_savefix_2xh100
Updated
atrost/nanochat-d24-matformer-ffnlog-fullattn-sft-xl
Updated
atrost/nanochat-d24-matformer-ffnlog-fullattn-sft-l
Updated
atrost/nanochat-d24-matformer-ffnlog-fullattn-sft-m
Updated
atrost/nanochat-d24-matformer-ffnlog-fullattn-sft-s
Updated
atrost/nanochat-d24-matformer-ffnlog-fullattn-sft
Updated
atrost/nanochat-d24-matformer-ffnlog-fullattn-20260507-xl
Updated
atrost/nanochat-d24-matformer-ffnlog-fullattn-20260507-l
Updated
atrost/nanochat-d24-matformer-ffnlog-fullattn-20260507-m
Updated
atrost/nanochat-d24-matformer-ffnlog-fullattn-20260507-s
Updated
datasets 18
atrost/OpenThoughts-Agent-v1-SFT-intersection-727
Viewer • Updated • 727 • 31
atrost/OpenThoughts-Agent-v1-RL-intersection-727
Viewer • Updated • 727 • 30
atrost/nanochat-d24-sft-chat-eval-v1
Viewer • Updated • 8 • 215
atrost/math_sft_40K_trl_think
Viewer • Updated • 39.9k • 29
atrost/math_sft_40K_trl
Viewer • Updated • 39.9k • 11
atrost/sft_rollouts_32
Viewer • Updated • 160k • 14
atrost/MATH-50-chunk-10
Viewer • Updated • 100 • 5
atrost/MATH-50-chunk-9
Viewer • Updated • 100 • 10
atrost/MATH-50-chunk-8
Viewer • Updated • 100 • 9
atrost/MATH-50-chunk-7
Viewer • Updated • 100 • 8