hi-todayis-jh AI Models

Tracked by OpenModelStats since Sep 16, 2026 · View on Hugging Face ↗

Tracked models
229
Downloads 30D
444
Total downloads
444
Total likes
0
Gained 7D
0

Most downloaded

  1. 1f-cov-l0-0-no-eos-qwen3-1.7b-compression-bs32-n16-32k-146103-finalSep 28, 202682
  2. 2maxrl-no-eos-qwen3-1.7b-compression-bs32-n16-32k-146103-finalSep 28, 202677
  3. 3per-context-rb-l0-0-qwen3-1.7b-compression-bs32-32k-146103-finalSep 28, 202677
  4. 4per-context-rb-l0-4096-no-eos-qwen3-1.7b-compression-bs32-32k-146102-finalSep 28, 202674
  5. 5l1-max-qwen3-1.7b-compression-100-6k-from80-mixed50-alpha3e-4-bs32-n8-32k-t1-146102-finalOct 6, 202614
  6. 6l1-exact-qwen3-1.7b-compression-100-6k-alpha3e-4-bs32-n8-32k-t1-146102-finalOct 5, 202614
  7. 7grpo-qwen3-1.7b-nemotron-leetcode-clean-3.2k-bs32-n8-verl091-146102-finalSep 29, 202614
  8. 8l4096-qwen3-1.7b-compression-bs32-n16-32k-t1-no-eos-verl091-146102-finalOct 2, 202614
  9. 9l1-exact-qwen3-1.7b-compression-100-4k-alpha3e-4-bs32-n8-32k-t1-146103-finalOct 5, 202613
  10. 10l0-qwen3-1.7b-compression-bs32-n16-32k-t1-no-eos-seqmean-verl091-146102-finalOct 1, 202611

Recently updated

  1. 1ouro-1.4b-thinking-grpo-native4-math-154711-20261009-ragged-rlOct 13, 20260
  2. 2ouro-1.4b-thinking-grpo-k8-ragged-math-154711-20261009-ragged-rlOct 13, 20260
  3. 3ouro-1.4b-thinking-grpo-lp0p2-native4-math-154712-20261009-ragged-rlOct 13, 20260
  4. 4ouro-1.4b-thinking-maxrl-fixed4-math-154712-20261008-maxrl-fixed4Oct 13, 20260
  5. 5ouro-1.4b-thinking-per-context-rb-c1024-analytic-glr2e-4-ragged-math-154712-20261009-ragged-rlOct 12, 20260
  6. 6ouro-1.4b-thinking-per-context-rb-c1024-analytic-glr3e-5-ragged-math-154712-20261009-ragged-rlOct 11, 20260
  7. 7ouro-1.4b-thinking-per-context-rb-c1024-analytic-ragged-math-154712-20261009-ragged-rlOct 11, 20260
  8. 8ouro-1.4b-thinking-per-context-rb-rerun-ragged-math-154711-20261009-ragged-rlOct 11, 20260
  9. 9ouro-1.4b-thinking-maxrl-ragged-math-154711-20261009-ragged-rlOct 11, 20260
  10. 10ouro-1.4b-thinking-per-context-rb-ragged-math-154712-20261009-ragged-rlOct 10, 20260

All models

All tracked models published by hi-todayis-jh
ModelDL 30D7D
l1-exact-qwen3-1.7b-compression-100-6k-alpha3e-4-bs32-n8-32k-t1-146102-step_80hi-todayis-jh/l1-exact-qwen3-1.7b-compression-100-6k-alpha3e-4-bs32-n8-32k-t1-146102-step_800—
l1-exact-qwen3-1.7b-compression-100-4k-alpha3e-4-bs32-n8-32k-t1-146103-step_40hi-todayis-jh/l1-exact-qwen3-1.7b-compression-100-4k-alpha3e-4-bs32-n8-32k-t1-146103-step_400—
l1-exact-qwen3-1.7b-compression-100-4k-alpha3e-4-bs32-n8-32k-t1-146103-step_20hi-todayis-jh/l1-exact-qwen3-1.7b-compression-100-4k-alpha3e-4-bs32-n8-32k-t1-146103-step_200—
l1-exact-qwen3-1.7b-compression-100-6k-alpha3e-4-bs32-n8-32k-t1-146102-step_100hi-todayis-jh/l1-exact-qwen3-1.7b-compression-100-6k-alpha3e-4-bs32-n8-32k-t1-146102-step_1000—
l4096-qwen3-1.7b-compression-bs32-n16-32k-t1-no-eos-verl091-146102-step_70hi-todayis-jh/l4096-qwen3-1.7b-compression-bs32-n16-32k-t1-no-eos-verl091-146102-step_700—
rloo-qwen3-1.7b-compression-official-hybrid8-bs32-n8-b128-32k-146103-finalhi-todayis-jh/rloo-qwen3-1.7b-compression-official-hybrid8-bs32-n8-b128-32k-146103-final0—
grpo-qwen3-1.7b-polaris-1-8-3200-bs32-32k-146102-step_40hi-todayis-jh/grpo-qwen3-1.7b-polaris-1-8-3200-bs32-32k-146102-step_400—
rloo-qwen3-1.7b-compression-official-hybrid8-bs32-n8-b128-32k-146103-step_40hi-todayis-jh/rloo-qwen3-1.7b-compression-official-hybrid8-bs32-n8-b128-32k-146103-step_400—
l1-exact-qwen3-1.7b-compression-bs32-n8-32k-t1-146103-step_40hi-todayis-jh/l1-exact-qwen3-1.7b-compression-bs32-n8-32k-t1-146103-step_400—
f-cov-l0-0-no-eos-qwen3-1.7b-compression-bs32-n16-32k-146103-step_30hi-todayis-jh/f-cov-l0-0-no-eos-qwen3-1.7b-compression-bs32-n16-32k-146103-step_300—
grpo-qwen3-1.7b-nemotron-leetcode-clean-3.2k-bs32-n8-verl091-146102-step_50hi-todayis-jh/grpo-qwen3-1.7b-nemotron-leetcode-clean-3.2k-bs32-n8-verl091-146102-step_500—
ouro-1.4b-thinking-per-context-rb-c1024-analytic-glr3e-5-ragged-math-154712-20261009-ragged-rlhi-todayis-jh/ouro-1.4b-thinking-per-context-rb-c1024-analytic-glr3e-5-ragged-math-154712-20261009-ragged-rl0—
grpo-qwen3-1.7b-nemotron-leetcode-clean-3.2k-bs32-n8-verl091-epoch2-146102-step_180hi-todayis-jh/grpo-qwen3-1.7b-nemotron-leetcode-clean-3.2k-bs32-n8-verl091-epoch2-146102-step_1800—
f-cov-qwen3-1.7b-compression-bs32-n16-32k-t1-no-eos-verl091-146103-step_30hi-todayis-jh/f-cov-qwen3-1.7b-compression-bs32-n16-32k-t1-no-eos-verl091-146103-step_300—
f-cov-l4096-qwen3-1.7b-compression-bs32-n16-32k-t1-no-eos-seqmean-verl091-146102-step_20hi-todayis-jh/f-cov-l4096-qwen3-1.7b-compression-bs32-n16-32k-t1-no-eos-seqmean-verl091-146102-step_200—
ouro-1.4b-thinking-per-context-rb-ragged-math-154712-20261009-ragged-rlhi-todayis-jh/ouro-1.4b-thinking-per-context-rb-ragged-math-154712-20261009-ragged-rl0—
grpo-qwen3-1.7b-nemotron-leetcode-clean-3.2k-bs32-n8-verl091-146102-step_90hi-todayis-jh/grpo-qwen3-1.7b-nemotron-leetcode-clean-3.2k-bs32-n8-verl091-146102-step_900—
fixed-n-rb-offset-cost-aware-marginrl-qwen3-1.7b-base-math12k-offset2048-token-mean-step_150hi-todayis-jh/fixed-n-rb-offset-cost-aware-marginrl-qwen3-1.7b-base-math12k-offset2048-token-mean-step_1500—
grpo-qwen3-1.7b-nemotron-leetcode-clean-3.2k-bs32-n8-verl091-epoch2-146102-step_110hi-todayis-jh/grpo-qwen3-1.7b-nemotron-leetcode-clean-3.2k-bs32-n8-verl091-epoch2-146102-step_1100—
grpo-qwen3-1.7b-taco-easy-3200-bs32-n8-seqs16-32k-146102-step_40hi-todayis-jh/grpo-qwen3-1.7b-taco-easy-3200-bs32-n8-seqs16-32k-146102-step_400—
f-cov-l0-0-no-eos-qwen3-1.7b-compression-bs32-n16-32k-146103-step_20hi-todayis-jh/f-cov-l0-0-no-eos-qwen3-1.7b-compression-bs32-n16-32k-146103-step_200—
l1-max-qwen3-1.7b-compression-100-6k-from80-mixed50-alpha3e-4-bs32-n8-32k-t1-146102-step_90hi-todayis-jh/l1-max-qwen3-1.7b-compression-100-6k-from80-mixed50-alpha3e-4-bs32-n8-32k-t1-146102-step_900—
rloo-qwen3-1.7b-compression-official-hybrid8-bs32-n8-b128-32k-146103-step_80hi-todayis-jh/rloo-qwen3-1.7b-compression-official-hybrid8-bs32-n8-b128-32k-146103-step_800—
grpo-qwen3-1.7b-polaris-1-8-3200-bs32-32k-146102-step_100hi-todayis-jh/grpo-qwen3-1.7b-polaris-1-8-3200-bs32-32k-146102-step_1000—
l0-qwen3-1.7b-compression-bs32-n16-32k-t1-no-eos-seqmean-verl091-146102-step_60hi-todayis-jh/l0-qwen3-1.7b-compression-bs32-n16-32k-t1-no-eos-seqmean-verl091-146102-step_600—