OpenModelStats

zjhhhh AI Models

Tracked by OpenModelStats since Aug 23, 2026 · View on Hugging Face ↗

Tracked models
91
Downloads 30D
0
Total downloads
0
Total likes
2
Gained 7D
0

Most downloaded

  1. 1fixed-n-rb-er-cost-marginrl-qwen3-1.7b-base-math12k-token-mean-run2-step_100Sep 6, 20260
  2. 2fixed-n-rb-offset-marginrl-qwen3-4b-base-polaris53k-offset512-token-mean-1epoch-step_120Sep 15, 20260
  3. 3l1-exact-mathverify-qwen3-1.7b-base-math12k-n512-step_100Aug 25, 20260
  4. 4maxrl-qwen3-4b-base-polaris53k-1epoch-step_60Sep 12, 20260
  5. 5fixed-n-rb-offset256-qwen3-1.7b-base-math12k-754f8ca2-step_100Sep 12, 20260
  6. 6l1-exact-mathverify-qwen3-1.7b-base-math12k-random100to4000-seed42-step_200Sep 2, 20260
  7. 7maxrl-qwen3-4b-base-polaris53k-1epoch-step_208Sep 15, 20260
  8. 8f-cov-offset256-qwen3-1.7b-base-math12k-d72a4f5d-step_100Sep 13, 20260
  9. 9fixed-n-rb-er-cost-marginrl-success-gated-qwen3-1.7b-base-math12k-token-mean-step_100Aug 23, 20260
  10. 10fixed-n-rb-cost-aware-marginrl-qwen3-1.7b-base-math12k-token-mean-rerun-step_100Sep 5, 20260

Recently updated

  1. 1fixed-n-rb-offset-marginrl-qwen3-4b-base-polaris53k-offset512-token-mean-1epoch-step_208Sep 15, 20260
  2. 2fixed-n-rb-offset-marginrl-qwen3-4b-base-polaris53k-offset512-token-mean-1epoch-step_180Sep 15, 20260
  3. 3rloo-qwen3-4b-polaris53k-len4096-seed79-step_60Sep 15, 20260
  4. 4fixed-n-rb-offset-marginrl-qwen3-4b-base-polaris53k-offset512-token-mean-1epoch-step_120Sep 15, 20260
  5. 5f-cov-offset512-qwen3-1.7b-base-math12k-49fbccca-step_150Sep 15, 20260
  6. 6fixed-n-rb-offset-marginrl-qwen3-4b-base-polaris53k-offset512-token-mean-1epoch-step_60Sep 15, 20260
  7. 7f-cov-offset512-qwen3-1.7b-base-math12k-49fbccca-step_100Sep 15, 20260
  8. 8f-cov-offset512-qwen3-1.7b-base-math12k-49fbccca-step_50Sep 15, 20260
  9. 9maxrl-qwen3-4b-base-polaris53k-1epoch-step_208Sep 15, 20260
  10. 10fixed-n-rb-offset512-qwen3-1.7b-base-math12k-8be8236f-step_150Sep 14, 20260

All models

All tracked models published by zjhhhh
ModelDL 30D7D
fixed-n-rb-offset-marginrl-qwen3-4b-base-polaris53k-offset512-token-mean-1epoch-step_120zjhhhh/fixed-n-rb-offset-marginrl-qwen3-4b-base-polaris53k-offset512-token-mean-1epoch-step_1200+0
l1-exact-mathverify-qwen3-1.7b-base-math12k-n512-step_100zjhhhh/l1-exact-mathverify-qwen3-1.7b-base-math12k-n512-step_1000+0
maxrl-qwen3-4b-base-polaris53k-1epoch-step_60zjhhhh/maxrl-qwen3-4b-base-polaris53k-1epoch-step_600+0
l1-exact-mathverify-qwen3-1.7b-base-math12k-random100to4000-seed42-step_200zjhhhh/l1-exact-mathverify-qwen3-1.7b-base-math12k-random100to4000-seed42-step_2000+0
fixed-n-rb-cost-aware-marginrl-qwen3-1.7b-base-math12k-token-mean-rerun-step_100zjhhhh/fixed-n-rb-cost-aware-marginrl-qwen3-1.7b-base-math12k-token-mean-rerun-step_1000+0
fixed-n-rb-offset256-qwen3-1.7b-base-math12k-754f8ca2-step_100zjhhhh/fixed-n-rb-offset256-qwen3-1.7b-base-math12k-754f8ca2-step_1000+0
f-cov-offset256-qwen3-1.7b-base-math12k-d72a4f5d-step_100zjhhhh/f-cov-offset256-qwen3-1.7b-base-math12k-d72a4f5d-step_1000+0
maxrl-qwen3-0.6b-polaris-4-8-bs16-n16-32k-1epoch-step_150zjhhhh/maxrl-qwen3-0.6b-polaris-4-8-bs16-n16-32k-1epoch-step_1500+0
fixed-n-rb-er-cost-marginrl-qwen3-1.7b-base-math12k-token-mean-run2-step_150zjhhhh/fixed-n-rb-er-cost-marginrl-qwen3-1.7b-base-math12k-token-mean-run2-step_1500+0
maxrl-qwen3-4b-base-polaris53k-1epoch-step_208zjhhhh/maxrl-qwen3-4b-base-polaris53k-1epoch-step_2080+0
fixed-n-rb-er-cost-marginrl-success-gated-qwen3-1.7b-base-math12k-token-mean-step_100zjhhhh/fixed-n-rb-er-cost-marginrl-success-gated-qwen3-1.7b-base-math12k-token-mean-step_1000+0
er_cost_marginrl_r1_distill_1.5b_compression_n16_b512_32k_lr1e-6_kl0_seed42-step_100zjhhhh/er_cost_marginrl_r1_distill_1.5b_compression_n16_b512_32k_lr1e-6_kl0_seed42-step_1000+0
fixed-n-rb-er-cost-marginrl-qwen3-1.7b-base-math12k-token-mean-fixed-q0p8-step_190zjhhhh/fixed-n-rb-er-cost-marginrl-qwen3-1.7b-base-math12k-token-mean-fixed-q0p8-step_1900+0
fixed-n-rb-er-cost-marginrl-qwen3-1.7b-base-math12k-token-mean-fixed-q0p8-step_200zjhhhh/fixed-n-rb-er-cost-marginrl-qwen3-1.7b-base-math12k-token-mean-fixed-q0p8-step_2000+0
fixed-n-rb-er-cost-marginrl-qwen3-1.7b-base-math12k-token-mean-fixed-q0p8-step_100zjhhhh/fixed-n-rb-er-cost-marginrl-qwen3-1.7b-base-math12k-token-mean-fixed-q0p8-step_1000+0
fixed-n-rb-er-cost-marginrl-success-gated-qwen3-1.7b-base-math12k-token-mean-step_50zjhhhh/fixed-n-rb-er-cost-marginrl-success-gated-qwen3-1.7b-base-math12k-token-mean-step_500+0
fixed-n-rb-er-cost-marginrl-qwen3-1.7b-base-math12k-token-mean-fixed-q0p8-step_170zjhhhh/fixed-n-rb-er-cost-marginrl-qwen3-1.7b-base-math12k-token-mean-fixed-q0p8-step_1700+0
l1-exact-mathverify-qwen3-1.7b-base-math12k-n512-step_230zjhhhh/l1-exact-mathverify-qwen3-1.7b-base-math12k-n512-step_2300+0
f-cov-offset256-qwen3-1.7b-base-math12k-d72a4f5d-step_50zjhhhh/f-cov-offset256-qwen3-1.7b-base-math12k-d72a4f5d-step_500+0
fixed-n-rb-er-cost-marginrl-qwen3-1.7b-base-math12k-token-mean-fixed-q0p8-step_150zjhhhh/fixed-n-rb-er-cost-marginrl-qwen3-1.7b-base-math12k-token-mean-fixed-q0p8-step_1500+0
fixed-n-rb-cost-aware-marginrl-qwen3-1.7b-base-math12k-token-mean-rerun-step_50zjhhhh/fixed-n-rb-cost-aware-marginrl-qwen3-1.7b-base-math12k-token-mean-rerun-step_500+0
maxrl-qwen3-0.6b-polaris-4-8-2epochs-step_158zjhhhh/maxrl-qwen3-0.6b-polaris-4-8-2epochs-step_1580+0
fixed-n-rb-offset512-qwen3-1.7b-base-math12k-8be8236f-step_100zjhhhh/fixed-n-rb-offset512-qwen3-1.7b-base-math12k-8be8236f-step_1000+0
fixed-n-rb-cost-aware-marginrl-qwen3-1.7b-base-math12k-token-mean-rerun-step_200zjhhhh/fixed-n-rb-cost-aware-marginrl-qwen3-1.7b-base-math12k-token-mean-rerun-step_2000+0
fixed-n-rb-er-cost-marginrl-qwen3-1.7b-base-math12k-token-mean-run2-step_100zjhhhh/fixed-n-rb-er-cost-marginrl-qwen3-1.7b-base-math12k-token-mean-run2-step_1000+0