atrost/Qwen3-1.7B-Base-SFT-40K
Updated
Avi Trost
atrost
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning? updated a model about 1 month ago
atrost/q1_dp0_loss_kl_pcgrad_b0150_savefix_2xh100 published a model about 1 month ago
atrost/q1_dp0_loss_kl_pcgrad_b0150_savefix_2xh100Organizations
atrost/Qwen3-1.7B-Base-dapo-pos-advantage-only
2B • Updated
atrost/Qwen3-1.7B-Base-dapo-neg-advantage-only
2B • Updated
atrost/Qwen3-1.7B-Base-math_rl_48k-N4-M4-rs-sft-20250820-181719-b3d9a23a
2B • Updated
atrost/flan-t5-large-pubmed_qa-pqa_labeled
Updated • 1
atrost/flan-t5-xl-pubmed_qa-pqa_labeled
Updated
atrost/flan-t5-Xxl-pubmed_qa-pqa_labeled
Updated
atrost/flan-t5-large-pubmed_qa-pqa_artificial
Updated • 1
atrost/flan-t5-xl-pubmed_qa-pqa_artificial
Updated
atrost/flan-t5-Xxl-pubmed_qa-pqa_artificial
Updated
atrost/flan-t5-small-pubmed_qa-pqa_labeled
Updated • 1