Commit History

Today

  1. Update README.md

    Verified signature
    ea9a45d

7 days ago

  1. Upload k2-horizon-3.7b-benchmarks.png

    Verified signature
    4525090
  2. Upload k2-horizon-3.7b-benchmarks.png

    Verified signature
    dc12ec6
  3. Update README.md

    Verified signature
    f78231e

21 days ago

  1. Support OpenAI-style text content lists (#7)⁠

    mingshan +1: hanseungwook
    9d280ff

  1. Update README.md with information on FTPO

    Verified signature
    d6e5432
  2. Update README.md with information on FTPO.

    Verified signature
    93c35f5

  1. Fix the tag name of anti doom loop checkpoint in README.md

    Verified signature
    c7d0261
  2. Update README.md to include anti doom loop checkpoint

    Verified signature
    35ba769
  3. Promote checkpoint anti_doom_loop_verified to main

    HF release automation
    fe504ef
  4. Publish checkpoint anti_doom_loop_verified⁠

    HF release automation
    0ec9899
  5. Fix typo and wording.

    Verified signature
    6e609f8
  6. Add anti-doom-loop paragraph

    Verified signature
    17701a5
  7. Update README.md

    Verified signature
    77cf611
  8. Document tool_call_format API options (#2)⁠

    hunterhector +1: hanseungwook
    641ee63

  1. Release artifacts updated.

    Verified signature
    943ce4e

  1. Delete files migration_manifest.json validation.json with huggingface_hub

    Verified signature
    85f683b

  1. Add a note on ckpt usage

    Verified signature
    242d92f

  1. Update model card

    Verified signature
    6360f70

  1. Preserve checkpoint history: rl_stemcode⁠

    HF release automation
    09568ba
  2. Publish checkpoint rl_stemcode⁠

    HF release automation
    8fdfbf0
  3. Preserve checkpoint history: rl_code⁠

    HF release automation
    747acd3
  4. Publish checkpoint rl_code⁠

    HF release automation
    79763ae
  5. Preserve checkpoint history: rl_math⁠

    HF release automation
    972a537
  6. Publish checkpoint rl_math⁠

    HF release automation
    d3279cd

  1. Fix typo

    Verified signature
    7a7d2c1
  2. Update ckpt progress

    Verified signature
    d237986

  1. Add details in RL stage in Training Overview.

    Verified signature
    9395c67
  2. Preserve checkpoint history: sft_2_500⁠

    HF release automation
    7c542d8
  3. Preserve checkpoint history: sft_2_1000⁠

    HF release automation
    3f9153f
  4. Preserve checkpoint history: sft_2_1500⁠

    HF release automation
    47bf9f4
  5. Preserve checkpoint history: sft_2_2000⁠

    HF release automation
    f705041
  6. Preserve checkpoint history: sft_2_2500⁠

    HF release automation
    481170a
  7. Preserve checkpoint history: sft_1_2000⁠

    HF release automation
    5fa6fe7
  8. Preserve checkpoint history: sft_1_4000⁠

    HF release automation
    f1df18d
  9. Preserve checkpoint history: sft_1_6000⁠

    HF release automation
    8f96a3c
  10. Preserve checkpoint history: sft_1_8000⁠

    HF release automation
    e1eb65d
  11. Preserve checkpoint history: sft_1_10000⁠

    HF release automation
    76646c0
  12. Preserve checkpoint history: mid_4_1000⁠

    HF release automation
    d9cc0e9
  13. Preserve checkpoint history: mid_4_2000⁠

    HF release automation
    aace30e
  14. Preserve checkpoint history: mid_4_3000⁠

    HF release automation
    4e6ed10
  15. Preserve checkpoint history: mid_4_4000⁠

    HF release automation
    00b8afd
  16. Preserve checkpoint history: mid_4_5000⁠

    HF release automation
    f748017
  17. Preserve checkpoint history: mid_4_6000⁠

    HF release automation
    a3bf52a
  18. Preserve checkpoint history: mid_4_7000⁠

    HF release automation
    1bcd87f
  19. Preserve checkpoint history: mid_4_8000⁠

    HF release automation
    9ed5257
  20. Preserve checkpoint history: mid_4_9000⁠

    HF release automation
    e53b5a5
  21. Preserve checkpoint history: mid_4_10000⁠

    HF release automation
    cc00ba7
  22. Preserve checkpoint history: mid_3_500⁠

    HF release automation
    c096dab
  23. Preserve checkpoint history: mid_3_1000⁠

    HF release automation
    8601d96