atrost/nanochat-d24-matformer-smlx-sft-l
Updated
Avi Trost
atrost
AI & ML interests
None yet
Recent Activity
upvoted a paper 29 days ago
When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning? updated a model 29 days ago
atrost/q1_dp0_loss_kl_pcgrad_b0150_savefix_2xh100 published a model 29 days ago
atrost/q1_dp0_loss_kl_pcgrad_b0150_savefix_2xh100Organizations
atrost/nanochat-d24-matformer-smlx-sft-m
Updated
atrost/nanochat-d24-matformer-smlx-sft-s
Updated
atrost/nanochat-d24-nested-k4-alpha01-sft-k4
Updated
atrost/nanochat-d24-nested-k4-alpha01-sft-k3
Updated
atrost/nanochat-d24-nested-k4-alpha01-sft-k2
Updated
atrost/nanochat-d24-nested-k4-alpha01-sft-k1
Updated
atrost/nanochat-d24-dense-xl-nestedmatch-sft
Updated
atrost/nanochat-d24-nested-k4-alpha01-sft
Updated
atrost/nanochat-d24-dense-s-nestedmatch-sft
Updated
atrost/nanochat-d24-dense-l-nestedmatch-sft
Updated
atrost/nanochat-d24-dense-m-nestedmatch-sft
Updated
atrost/nanochat-d24-matformer-smlx-sft
Updated
atrost/nanochat-sft-condor-smoke
Updated
atrost/climbmix-stairformer-353m-extracted-nested-94m-1p2b-h100-vllm
0.6B • Updated • 2
atrost/climbmix-baseline-small-asymmetric-94m-1p2b-h100-vllm
0.6B • Updated • 6
atrost/climbmix-stairformer-353m-1p2b-h100-vllm
0.6B • Updated • 3
atrost/climbmix-matformer-353m-1p2b-h100-xl-vllm
0.4B • Updated • 3
atrost/climbmix-matformer-353m-1p2b-h100-l-vllm
0.3B • Updated • 1
atrost/climbmix-matformer-353m-1p2b-h100-m-vllm
0.2B • Updated • 31
atrost/climbmix-matformer-353m-1p2b-h100-s-vllm
0.2B • Updated • 5
atrost/climbmix-matformer-353m-1p2b-h100-xl
0.4B • Updated • 3
atrost/climbmix-matformer-353m-1p2b-h100-l
0.3B • Updated • 6
atrost/climbmix-matformer-353m-1p2b-h100-m
0.2B • Updated • 2
atrost/climbmix-matformer-353m-1p2b-h100-s
0.2B • Updated • 3
atrost/climbmix-matformer-353m-1p2b-h100
0.4B • Updated • 8
atrost/climbmix-stairformer-353m-extracted-nested-94m-1p2b-h100
94.3M • Updated • 6
atrost/climbmix-stairformer-353m-1p2b-h100
0.6B • Updated • 9
atrost/climbmix-baseline-small-asymmetric-94m-1p2b-h100
Updated • 1
atrost/climbmix-baseline-large-353m-1p2b-h100
0.4B • Updated • 1