zhezi12138 AI Models

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

Tracked models
74
Downloads 30D
16
Total downloads
16
Total likes
0
Gained 7D
0

Most downloaded

  1. 1Qwen3-4B-formal-r1-RL-50iter-seed42Sep 7, 202616
  2. 2qwen3-4B-coding-mbpp-random-per-layer50-seed42-zfgbcSep 22, 20260
  3. 3qwen3-1.7B-math-gradimp-train-bottom50-lr7e-6-seed42-zfgbcSep 15, 20260
  4. 4Qwen3-4B-coding-mbpp-gradimp-top50-lr3e-6-seed41Aug 31, 20260
  5. 5Qwen3-4B-rlvr-ifeval-gradimp-train-bottom50-seed43Aug 29, 20260
  6. 6Qwen3-4B-rlvr-ifeval-gradimp-train-bottom50-seed42-zfgbcSep 5, 20260
  7. 7qwen3-1.7B-mbpp-gradimp-train-top70Sep 2, 20260
  8. 8qwen3-1.7B-cont-ifevalfulltrain-i599-math-fulltrain-lr1e-6Sep 15, 20260
  9. 9qwen3-1.7B-mbpp-gradimp-train-top50-seed42-zfgbcSep 7, 20260
  10. 10qwen3-1.7B-cont-ifevalfullattn-i599-math-allattn-lr3e-6Sep 15, 20260

Recently updated

  1. 1qwen3-1.7B-coding-mbpp-random-per-layer50-seed42-zfgbcSep 24, 20260
  2. 2qwen3-1.7B-rlvr-ifeval-random-per-layer50-seed42-zfgbcSep 24, 20260
  3. 3qwen3-1.7B-dapo-math-random-per-layer50-seed42-zfgbcSep 23, 20260
  4. 4qwen3-4B-coding-mbpp-random-per-layer50-seed42-zfgbcSep 22, 20260
  5. 5qwen3-1.7B-rr50-2way-ifeval-lr3e-6-zfgbcSep 21, 20260
  6. 6qwen3-4B-dapo-math-random-per-layer50-seed42-zfgbcSep 21, 20260
  7. 7qwen3-1.7B-cont-rr50-ifeval-math-lr3e-6-zfgbcSep 21, 20260
  8. 8mistral-7B-instruct-rlvr-ifeval-allattn-lr2e-6-seed42-zfgbc-i400Sep 21, 20260
  9. 9mistral-7B-instruct-rlvr-ifeval-bottom50-lr2e-6-seed42-zfgbc-i400Sep 20, 20260
  10. 10qwen3-4B-rlvr-ifeval-random-per-layer50-seed42-zfgbc-rerunSep 20, 20260

All models

All tracked models published by zhezi12138
ModelDL 30D7D
Qwen3-4B-formal-r1-RL-50iter-seed42zhezi12138/qwen3-4b-formal-r1-rl-50iter-seed4216+0
qwen3-1.7B-rlvr-ifeval-random-per-layer50-seed42-zfgbczhezi12138/qwen3-1.7b-rlvr-ifeval-random-per-layer50-seed42-zfgbc0—
qwen3-1.7B-mbpp-gradimp-train-top10-lr5e-6-zfgbczhezi12138/qwen3-1.7b-mbpp-gradimp-train-top10-lr5e-6-zfgbc0+0
qwen3-1.7B-mbpp-gradimp-train-top90zhezi12138/qwen3-1.7b-mbpp-gradimp-train-top900+0
qwen3-1.7B-cont-ifevalfullattn-i599-math-allattn-lr3e-6zhezi12138/qwen3-1.7b-cont-ifevalfullattn-i599-math-allattn-lr3e-60+0
Qwen3-4B-coding-mbpp-gradimp-top50-lr3e-6-seed41zhezi12138/qwen3-4b-coding-mbpp-gradimp-top50-lr3e-6-seed410+0
Qwen3-4B-rlvr-ifeval-gradimp-train-bottom50-seed43zhezi12138/qwen3-4b-rlvr-ifeval-gradimp-train-bottom50-seed430+0
qwen3-1.7B-mbpp-gradimp-train-top70zhezi12138/qwen3-1.7b-mbpp-gradimp-train-top700+0
qwen3-1.7B-mbpp-gradimp-train-top50-seed42-zfgbczhezi12138/qwen3-1.7b-mbpp-gradimp-train-top50-seed42-zfgbc0+0
qwen3-4B-rlvr-ifeval-gradimp-train-bottom50-lr7e-6-seed42-zfgbczhezi12138/qwen3-4b-rlvr-ifeval-gradimp-train-bottom50-lr7e-6-seed42-zfgbc0—
qwen3-1.7B-math-gradimp-train-bottom50-lr7e-6-seed42-zfgbczhezi12138/qwen3-1.7b-math-gradimp-train-bottom50-lr7e-6-seed42-zfgbc0+0
qwen3-1.7B-cont-ifevalfulltrain-i599-math-fulltrain-lr1e-6zhezi12138/qwen3-1.7b-cont-ifevalfulltrain-i599-math-fulltrain-lr1e-60+0
qwen3-4B-rr50-2way-mbpp-lr3e-6-zfgbczhezi12138/qwen3-4b-rr50-2way-mbpp-lr3e-6-zfgbc0+0
qwen3-1.7B-rr50-2way-ifeval-lr3e-6-zfgbczhezi12138/qwen3-1.7b-rr50-2way-ifeval-lr3e-6-zfgbc0—
qwen3-4B-coding-mbpp-random-per-layer50-seed42-zfgbczhezi12138/qwen3-4b-coding-mbpp-random-per-layer50-seed42-zfgbc0—
qwen3-4B-rlvr-ifeval-random-per-layer50-seed42-zfgbc-rerunzhezi12138/qwen3-4b-rlvr-ifeval-random-per-layer50-seed42-zfgbc-rerun0—
mistral-7B-instruct-rlvr-ifeval-top50-lr2e-6-seed42-zfgbc-i400zhezi12138/mistral-7b-instruct-rlvr-ifeval-top50-lr2e-6-seed42-zfgbc-i4000—
Qwen3-4B-rlvr-ifeval-gradimp-train-bottom50-seed32-zfgbczhezi12138/qwen3-4b-rlvr-ifeval-gradimp-train-bottom50-seed32-zfgbc0+0
qwen3-1.7B-mbpp-gradimp-train-top30-zfgbczhezi12138/qwen3-1.7b-mbpp-gradimp-train-top30-zfgbc0+0
qwen3-1.7B-mbpp-gradimp-train-top70-zfgbczhezi12138/qwen3-1.7b-mbpp-gradimp-train-top70-zfgbc0+0
Qwen3-4B-rlvr-ifeval-gradimp-train-top50-seed32-zfgbczhezi12138/qwen3-4b-rlvr-ifeval-gradimp-train-top50-seed32-zfgbc0+0
Qwen3-4B-cont-dapotop50i399-rlvr-dapobot50-lr3e-6-zfgbczhezi12138/qwen3-4b-cont-dapotop50i399-rlvr-dapobot50-lr3e-6-zfgbc0+0
qwen3-1.7B-mbpp-gradimp-train-top90-zfgbczhezi12138/qwen3-1.7b-mbpp-gradimp-train-top90-zfgbc0+0
qwen3-4B-cont-mathrr50-rlvrifeval-rr50-lr3e-6-zfgbczhezi12138/qwen3-4b-cont-mathrr50-rlvrifeval-rr50-lr3e-6-zfgbc0+0
qwen3-1.7B-coding-mbpp-random-per-layer50-seed42-zfgbczhezi12138/qwen3-1.7b-coding-mbpp-random-per-layer50-seed42-zfgbc0—