budget-internalization-iclr2027 AI Models

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

Tracked models
45
Downloads 30D
1,914
Total downloads
1,914
Total likes
1
Gained 7D
0

Most downloaded

  1. 1nemotron3-nano-4b-8k-grpo-hardyman-s300Sep 23, 2026381
  2. 2nemotron3-nano-4b-4k-grpo-steadymagpie-s300Sep 23, 2026306
  3. 3nemotron3-nano-4b-16k-grpo-firmbeetle-s120Sep 23, 2026306
  4. 4nemotron3-nano-4b-2k-grpo-topdane-s300Sep 23, 2026183
  5. 5nemotron3-nano-4b-1k-grpo-usefulhippo-s300Sep 23, 2026176
  6. 6nemotron3-nano-4b-2k-grpo-reasoninggym-coolbengal-s300Sep 25, 2026139
  7. 7qwen3.5-4b-4k-grpo-sunnyfoal-s300Sep 23, 202620
  8. 8qwen3.5-4b-4k-grpo-overlong-penalty-awaretick-s300Sep 23, 202615
  9. 9qwen3.5-4b-16k-grpo-reasoninggym-restedmarlin-s300Sep 25, 202615
  10. 10qwen3.5-4b-32k-grpo-validlemur-s300Sep 23, 202614

Recently updated

  1. 1qwen3.5-4b-4k-grpo-livecodebench-crackgannet-s240Sep 25, 20267
  2. 2qwen3.5-4b-2k-grpo-spreadsheet-happyraven-s100Sep 25, 20269
  3. 3qwen3.5-4b-1k-grpo-spreadsheet-selectsloth-s100Sep 25, 20268
  4. 4qwen3.5-4b-4k-grpo-lean-boldthrush-s70Sep 25, 202612
  5. 5qwen3.5-4b-2k-grpo-lean-upwardgull-s50Sep 25, 202610
  6. 6qwen3.5-4b-16k-grpo-budget-after-think-tidycobra-s300Sep 25, 202613
  7. 7qwen3.5-4b-16k-grpo-budget-system-neatgrouse-s300Sep 25, 202613
  8. 8qwen3.5-4b-16k-grpo-budget-user-kindelf-s300Sep 25, 202611
  9. 9qwen3.5-4b-4k-grpo-budget-after-think-epictuna-s210Sep 25, 202610
  10. 10qwen3.5-4b-4k-grpo-budget-system-viableroughy-s250Sep 25, 202610

All models

All tracked models published by budget-internalization-iclr2027
ModelDL 30D7D
gemma4-e2b-1k-grpo-luckymarmot-s300budget-internalization-iclr2027/gemma4-e2b-1k-grpo-luckymarmot-s30011—
qwen3.5-4b-8k-grpo-overlong-penalty-awareshrimp-s300budget-internalization-iclr2027/qwen3.5-4b-8k-grpo-overlong-penalty-awareshrimp-s30011—
qwen3.5-4b-2k-grpo-lean-upwardgull-s50budget-internalization-iclr2027/qwen3.5-4b-2k-grpo-lean-upwardgull-s5010—
qwen3.5-4b-4k-grpo-budget-user-selectgnu-s260budget-internalization-iclr2027/qwen3.5-4b-4k-grpo-budget-user-selectgnu-s26010—
gemma4-e2b-2k-grpo-reasoninggym-smartcamel-s300budget-internalization-iclr2027/gemma4-e2b-2k-grpo-reasoninggym-smartcamel-s30010—
gemma4-e2b-1k-grpo-reasoninggym-petbadger-s300budget-internalization-iclr2027/gemma4-e2b-1k-grpo-reasoninggym-petbadger-s30010—
qwen3.5-4b-4k-sft-forced-superoriole-s386budget-internalization-iclr2027/qwen3.5-4b-4k-sft-forced-superoriole-s38610—
qwen3.5-4b-4k-grpo-reasoninggym-easyturkey-s300budget-internalization-iclr2027/qwen3.5-4b-4k-grpo-reasoninggym-easyturkey-s30010—
qwen3.5-4b-4k-grpo-budget-after-think-epictuna-s210budget-internalization-iclr2027/qwen3.5-4b-4k-grpo-budget-after-think-epictuna-s21010—
qwen3.5-4b-4k-grpo-budget-system-viableroughy-s250budget-internalization-iclr2027/qwen3.5-4b-4k-grpo-budget-system-viableroughy-s25010—
qwen3.5-4b-8k-grpo-kl0.001-tenderbug-s300budget-internalization-iclr2027/qwen3.5-4b-8k-grpo-kl0.001-tenderbug-s30010—
qwen3.5-4b-4k-sft-pumpedjackal-s90budget-internalization-iclr2027/qwen3.5-4b-4k-sft-pumpedjackal-s909—
qwen3.5-4b-8k-grpo-overlong-mask-deeplocust-s300budget-internalization-iclr2027/qwen3.5-4b-8k-grpo-overlong-mask-deeplocust-s3009—
qwen3.5-4b-16k-grpo-eagerminnow-s300budget-internalization-iclr2027/qwen3.5-4b-16k-grpo-eagerminnow-s3009—
qwen3.5-4b-2k-grpo-spreadsheet-happyraven-s100budget-internalization-iclr2027/qwen3.5-4b-2k-grpo-spreadsheet-happyraven-s1009—
qwen3.5-4b-1k-grpo-spreadsheet-selectsloth-s100budget-internalization-iclr2027/qwen3.5-4b-1k-grpo-spreadsheet-selectsloth-s1008—
qwen3.5-4b-4k-grpo-overlong-mask-selectasp-s300budget-internalization-iclr2027/qwen3.5-4b-4k-grpo-overlong-mask-selectasp-s3007—
gemma4-e2b-2k-grpo-superworm-s300budget-internalization-iclr2027/gemma4-e2b-2k-grpo-superworm-s3007—
qwen3.5-4b-4k-grpo-livecodebench-crackgannet-s240budget-internalization-iclr2027/qwen3.5-4b-4k-grpo-livecodebench-crackgannet-s2407—
gemma4-e2b-4k-grpo-merrydingo-s300budget-internalization-iclr2027/gemma4-e2b-4k-grpo-merrydingo-s3005—