sandeep123 AI Models

Tracked by OpenModelStats since Aug 24, 2026 · View on Hugging Face ↗

Tracked models
149
Downloads 30D
1,166
Total downloads
1,490
Total likes
7
Gained 7D
28

Most downloaded

  1. 1ML-LaySum-Qwen3-1.7B-SFTSep 24, 2026156
  2. 2ML-LaySum-Gemma2-2B-Instruct-SFTOct 1, 2026105
  3. 3mathbf-grpo-temp12-step1100Sep 6, 202622
  4. 4mathbf-grpo-temp12-step900Sep 6, 202620
  5. 5mathbf-grpo-cliphigh-step1400Sep 6, 202616
  6. 6mathbf-grpo-vanilla-step1400Sep 6, 202616
  7. 7mathbf-grpo-entropy-step400Sep 6, 202615
  8. 8sqabf-grpo-vanilla-step300Sep 6, 202614
  9. 9math-grpo-temp12-step300Sep 2, 202614
  10. 10stride-math-a1-step1300Sep 7, 202614

Recently updated

  1. 1ML-LaySum-Gemma2-2B-Instruct-SFTOct 1, 2026105
  2. 2stride-qwen3-4b-allref-correctonly-local-positive-20260925Sep 28, 20260
  3. 3stride-qwen3-4b-allref-correctonly-token-uniform-20260925Sep 28, 20260
  4. 4stride-qwen3-1.7b-allref-correctonly-kl0-local-positive-20260925-resumeSep 26, 20260
  5. 5stride-qwen3-1.7b-allref-correctonly-kl0-token-uniform-20260925Sep 25, 20260
  6. 6stride-qwen3-1.7b-allref-correctonly-kl0-token-uniform-20260925-resume-gt3dSep 25, 20260
  7. 7stride-qwen3-1.7b-correctonly-kl0-local-positive-20260925Sep 25, 20260
  8. 8stride-qwen3-1.7b-allref-correctonly-kl0-local-positive-20260925Sep 25, 20260
  9. 9stride-qwen3-1.7b-correctonly-kl0-token-uniform-20260925Sep 25, 20260
  10. 10stride-qwen3-1.7b-allref-correctonly-token-uniform-20260925Sep 25, 20260

All models

All tracked models published by sandeep123
ModelDL 30D7D
math-dqo-a1-step700sandeep123/math-dqo-a1-step7007+0
math-grpo-vanilla-step1300sandeep123/math-grpo-vanilla-step13007+0
sqa-dqo-a1-step400sandeep123/sqa-dqo-a1-step4007+0
sqa-grpo-cliphigh-step400sandeep123/sqa-grpo-cliphigh-step4006+1
sqa-grpo-cliphigh-step300sandeep123/sqa-grpo-cliphigh-step3006+3
sqa-dqo-a1-step1000sandeep123/sqa-dqo-a1-step10006+0
sqa-grpo-cliphigh-step1100sandeep123/sqa-grpo-cliphigh-step11006+1
sqa-grpo-vanilla-step300sandeep123/sqa-grpo-vanilla-step3006+1
sqa-grpo-temp12-step800sandeep123/sqa-grpo-temp12-step8006+2
sqa-grpo-vanilla-step1200sandeep123/sqa-grpo-vanilla-step12005+2
sqa-grpo-vanilla-step900sandeep123/sqa-grpo-vanilla-step9005+2
sqa-grpo-entropy-step500sandeep123/sqa-grpo-entropy-step5004+1
sqa-grpo-entropy-step200sandeep123/sqa-grpo-entropy-step2004+1
sqa-grpo-entropy-step1200sandeep123/sqa-grpo-entropy-step12004+1
sqa-grpo-temp12-step200sandeep123/sqa-grpo-temp12-step2004+2
sqa-grpo-temp12-step900sandeep123/sqa-grpo-temp12-step9004+2
dapo-qwen3-1.7b-nonthinking-2048-20260918sandeep123/dapo-qwen3-1.7b-nonthinking-2048-202609180—
mathbf-grpo-temp12-step1400sandeep123/mathbf-grpo-temp12-step14000+0
stride-stride-a1-step1300sandeep123/stride-stride-a1-step13000+0
stride-qwen3-4b-stabilized-2048-local_positive-20260916sandeep123/stride-qwen3-4b-stabilized-2048-local_positive-202609160—
stride-stride-a1-step900sandeep123/stride-stride-a1-step9000+0
stride-qwen3-4b-2048-token_uniform-20260915sandeep123/stride-qwen3-4b-2048-token_uniform-202609150+0
stride-qwen3-4b-2048-local_positive-alpha2-20260915sandeep123/stride-qwen3-4b-2048-local_positive-alpha2-202609150+0
stride-qwen3-1.7b-allref-correctonly-token-uniform-20260925sandeep123/stride-qwen3-1.7b-allref-correctonly-token-uniform-202609250—
stride-qwen3-1.7b-allref-correctonly-kl0-token-uniform-20260925sandeep123/stride-qwen3-1.7b-allref-correctonly-kl0-token-uniform-202609250—