Hugging Face's logo

niklastr
/
dipper

Model card Files
xet
 Community
niklastr commited on
Commit
8d10609
·
verified ·
1 Parent(s): c3a11da

Normalize DIPPER checkpoint layout

Browse files
Files changed (40) hide show
  1. checkpoints/{dipper_15m/core/d_scaling/bin1024/80n/dipper_15m_core_bin1024_d_scaling_80n_step_3938.ckpt → 0_015B/core/1024_d_scaling/80n/dipper_0_015B_core_1024_d_scaling_80n_step_3938.ckpt} +0 -0
  2. checkpoints/{dipper_15m/core/ws_scaling/bin1024/dipper_15m_core_bin1024_ws_scaling_step_7875.ckpt → 0_015B/core/1024_ws_scaling/dipper_0_015B_core_1024_ws_scaling_step_7875.ckpt} +0 -0
  3. checkpoints/{dipper_15m/core/d_scaling/bin256/5n/dipper_15m_core_bin256_d_scaling_5n_step_248.ckpt → 0_015B/core/256_d_scaling/05n/dipper_0_015B_core_256_d_scaling_5n_step_248.ckpt} +0 -0
  4. checkpoints/{dipper_15m/core/d_scaling/bin256/10n/dipper_15m_core_bin256_d_scaling_10n_step_494.ckpt → 0_015B/core/256_d_scaling/10n/dipper_0_015B_core_256_d_scaling_10n_step_494.ckpt} +0 -0
  5. checkpoints/{dipper_15m/core/d_scaling/bin256/20n/dipper_15m_core_bin256_d_scaling_20n_step_986.ckpt → 0_015B/core/256_d_scaling/20n/dipper_0_015B_core_256_d_scaling_20n_step_986.ckpt} +0 -0
  6. checkpoints/{dipper_15m/core/d_scaling/bin256/40n/dipper_15m_core_bin256_d_scaling_40n_step_1970.ckpt → 0_015B/core/256_d_scaling/40n/dipper_0_015B_core_256_d_scaling_40n_step_1970.ckpt} +0 -0
  7. checkpoints/{dipper_15m/core/d_scaling/bin256/80n/dipper_15m_core_bin256_d_scaling_80n_step_3938.ckpt → 0_015B/core/256_d_scaling/80n/dipper_0_015B_core_256_d_scaling_80n_step_3938.ckpt} +0 -0
  8. checkpoints/{dipper_15m/core/ws_scaling/bin256/dipper_15m_core_bin256_ws_scaling_step_7875.ckpt → 0_015B/core/256_ws_scaling/dipper_0_015B_core_256_ws_scaling_step_7875.ckpt} +0 -0
  9. checkpoints/{dipper_15m/core/d_scaling/bin4096/5n/dipper_15m_core_bin4096_d_scaling_5n_step_248.ckpt → 0_015B/core/4096_d_scaling/05n/dipper_0_015B_core_4096_d_scaling_5n_step_248.ckpt} +0 -0
  10. checkpoints/{dipper_15m/core/d_scaling/bin4096/10n/dipper_15m_core_bin4096_d_scaling_10n_step_494.ckpt → 0_015B/core/4096_d_scaling/10n/dipper_0_015B_core_4096_d_scaling_10n_step_494.ckpt} +0 -0
  11. checkpoints/{dipper_15m/core/d_scaling/bin4096/20n/dipper_15m_core_bin4096_d_scaling_20n_step_986.ckpt → 0_015B/core/4096_d_scaling/20n/dipper_0_015B_core_4096_d_scaling_20n_step_986.ckpt} +0 -0
  12. checkpoints/{dipper_15m/core/d_scaling/bin4096/40n/dipper_15m_core_bin4096_d_scaling_40n_step_1970.ckpt → 0_015B/core/4096_d_scaling/40n/dipper_0_015B_core_4096_d_scaling_40n_step_1970.ckpt} +0 -0
  13. checkpoints/{dipper_15m/core/d_scaling/bin4096/80n/dipper_15m_core_bin4096_d_scaling_80n_step_3938.ckpt → 0_015B/core/4096_d_scaling/80n/dipper_0_015B_core_4096_d_scaling_80n_step_3938.ckpt} +0 -0
  14. checkpoints/{dipper_15m/core/ws_scaling/bin4096/dipper_15m_core_bin4096_ws_scaling_step_7875.ckpt → 0_015B/core/4096_ws_scaling/dipper_0_015B_core_4096_ws_scaling_step_7875.ckpt} +0 -0
  15. checkpoints/{dipper_15m/core/d_scaling/bin65537/5n/dipper_15m_core_bin65537_d_scaling_5n_step_594.ckpt → 0_015B/core/65537_d_scaling/05n/dipper_0_015B_core_65537_d_scaling_5n_step_594.ckpt} +0 -0
  16. checkpoints/{dipper_15m/core/d_scaling/bin65537/10n/dipper_15m_core_bin65537_d_scaling_10n_step_1188.ckpt → 0_015B/core/65537_d_scaling/10n/dipper_0_015B_core_65537_d_scaling_10n_step_1188.ckpt} +0 -0
  17. checkpoints/{dipper_15m/core/d_scaling/bin65537/20n/dipper_15m_core_bin65537_d_scaling_20n_step_2376.ckpt → 0_015B/core/65537_d_scaling/20n/dipper_0_015B_core_65537_d_scaling_20n_step_2376.ckpt} +0 -0
  18. checkpoints/{dipper_15m/core/d_scaling/bin65537/40n/dipper_15m_core_bin65537_d_scaling_40n_step_4752.ckpt → 0_015B/core/65537_d_scaling/40n/dipper_0_015B_core_65537_d_scaling_40n_step_4752.ckpt} +0 -0
  19. checkpoints/{dipper_15m/core/d_scaling/bin65537/80n/dipper_15m_core_bin65537_d_scaling_80n_step_9504.ckpt → 0_015B/core/65537_d_scaling/80n/dipper_0_015B_core_65537_d_scaling_80n_step_9504.ckpt} +0 -0
  20. checkpoints/{dipper_15m/core/ws_scaling/bin65537/dipper_15m_core_bin65537_ws_scaling_step_19008.ckpt → 0_015B/core/65537_ws_scaling/dipper_0_015B_core_65537_ws_scaling_step_19008.ckpt} +0 -0
  21. checkpoints/{dipper_1_7b/d_scaling/qwen3_1_7b_d_scaling_10k_step_12000.ckpt → 1_7B/qwen/d_scaling/dipper_1_7B_qwen_d_scaling_10k_step_12000.ckpt} +0 -0
  22. checkpoints/{dipper_1_7b/d_scaling/qwen3_1_7b_d_scaling_160k_step_192000.ckpt → 1_7B/qwen/d_scaling/dipper_1_7B_qwen_d_scaling_160k_step_192000.ckpt} +0 -0
  23. checkpoints/{dipper_1_7b/d_scaling/qwen3_1_7b_d_scaling_20k_step_24000.ckpt → 1_7B/qwen/d_scaling/dipper_1_7B_qwen_d_scaling_20k_step_24000.ckpt} +0 -0
  24. checkpoints/{dipper_1_7b/d_scaling/qwen3_1_7b_d_scaling_40k_step_48000.ckpt → 1_7B/qwen/d_scaling/dipper_1_7B_qwen_d_scaling_40k_step_48000.ckpt} +0 -0
  25. checkpoints/{dipper_1_7b/d_scaling/qwen3_1_7b_d_scaling_80k_step_96000.ckpt → 1_7B/qwen/d_scaling/dipper_1_7B_qwen_d_scaling_80k_step_96000.ckpt} +0 -0
  26. checkpoints/{dipper_1_7b/freesolv/qwen3_1_7b_freesolv_step_10000.ckpt → 1_7B/qwen/freesolv/dipper_1_7B_qwen_freesolv_step_10000.ckpt} +0 -0
  27. checkpoints/{dipper_1_7b/freesolv/qwen3_1_7b_freesolv_step_135000.ckpt → 1_7B/qwen/freesolv/dipper_1_7B_qwen_freesolv_step_135000.ckpt} +0 -0
  28. checkpoints/{dipper_1_7b/freesolv/qwen3_1_7b_freesolv_step_20000.ckpt → 1_7B/qwen/freesolv/dipper_1_7B_qwen_freesolv_step_20000.ckpt} +0 -0
  29. checkpoints/{dipper_1_7b/freesolv/qwen3_1_7b_freesolv_step_40000.ckpt → 1_7B/qwen/freesolv/dipper_1_7B_qwen_freesolv_step_40000.ckpt} +0 -0
  30. checkpoints/{dipper_1_7b/freesolv/qwen3_1_7b_freesolv_step_5000.ckpt → 1_7B/qwen/freesolv/dipper_1_7B_qwen_freesolv_step_5000.ckpt} +0 -0
  31. checkpoints/{dipper_1_7b/freesolv/qwen3_1_7b_freesolv_step_80000.ckpt → 1_7B/qwen/freesolv/dipper_1_7B_qwen_freesolv_step_80000.ckpt} +0 -0
  32. checkpoints/{dipper_1_7b/implicit/01f45245_5557923_step_30000.ckpt → 1_7B/qwen/implicit/dipper_1_7B_qwen_implicit_01f45245_5557923_step_30000.ckpt} +0 -0
  33. checkpoints/{dipper_1_7b/implicit/01f45245_5557923_step_35000.ckpt → 1_7B/qwen/implicit/dipper_1_7B_qwen_implicit_01f45245_5557923_step_35000.ckpt} +0 -0
  34. checkpoints/{dipper_1_7b/implicit/01f45245_5557923_step_40000.ckpt → 1_7B/qwen/implicit/dipper_1_7B_qwen_implicit_01f45245_5557923_step_40000.ckpt} +0 -0
  35. checkpoints/{dipper_1_7b/scaling/qwen3_1_7b_ws_scaling_step_10000.ckpt → 1_7B/qwen/ws_scaling/dipper_1_7B_qwen_ws_scaling_step_10000.ckpt} +0 -0
  36. checkpoints/{dipper_1_7b/scaling/qwen3_1_7b_ws_scaling_step_20000.ckpt → 1_7B/qwen/ws_scaling/dipper_1_7B_qwen_ws_scaling_step_20000.ckpt} +0 -0
  37. checkpoints/{dipper_1_7b/scaling/qwen3_1_7b_ws_scaling_step_40000.ckpt → 1_7B/qwen/ws_scaling/dipper_1_7B_qwen_ws_scaling_step_40000.ckpt} +0 -0
  38. checkpoints/{dipper_1_7b/scaling/qwen3_1_7b_ws_scaling_step_5000.ckpt → 1_7B/qwen/ws_scaling/dipper_1_7B_qwen_ws_scaling_step_5000.ckpt} +0 -0
  39. checkpoints/{dipper_1_7b/scaling/qwen3_1_7b_ws_scaling_step_80000.ckpt → 1_7B/qwen/ws_scaling/dipper_1_7B_qwen_ws_scaling_step_80000.ckpt} +0 -0
  40. checkpoints/{dipper_1_7b/scaling_rescue/qwen3_1_7b_ws_scaling_rescue_step_160000.ckpt → 1_7B/qwen/ws_scaling_rescue/dipper_1_7B_qwen_ws_scaling_rescue_step_160000.ckpt} +0 -0
checkpoints/{dipper_15m/core/d_scaling/bin1024/80n/dipper_15m_core_bin1024_d_scaling_80n_step_3938.ckpt → 0_015B/core/1024_d_scaling/80n/dipper_0_015B_core_1024_d_scaling_80n_step_3938.ckpt} RENAMED
File without changes
checkpoints/{dipper_15m/core/ws_scaling/bin1024/dipper_15m_core_bin1024_ws_scaling_step_7875.ckpt → 0_015B/core/1024_ws_scaling/dipper_0_015B_core_1024_ws_scaling_step_7875.ckpt} RENAMED
File without changes
checkpoints/{dipper_15m/core/d_scaling/bin256/5n/dipper_15m_core_bin256_d_scaling_5n_step_248.ckpt → 0_015B/core/256_d_scaling/05n/dipper_0_015B_core_256_d_scaling_5n_step_248.ckpt} RENAMED
File without changes
checkpoints/{dipper_15m/core/d_scaling/bin256/10n/dipper_15m_core_bin256_d_scaling_10n_step_494.ckpt → 0_015B/core/256_d_scaling/10n/dipper_0_015B_core_256_d_scaling_10n_step_494.ckpt} RENAMED
File without changes
checkpoints/{dipper_15m/core/d_scaling/bin256/20n/dipper_15m_core_bin256_d_scaling_20n_step_986.ckpt → 0_015B/core/256_d_scaling/20n/dipper_0_015B_core_256_d_scaling_20n_step_986.ckpt} RENAMED
File without changes
checkpoints/{dipper_15m/core/d_scaling/bin256/40n/dipper_15m_core_bin256_d_scaling_40n_step_1970.ckpt → 0_015B/core/256_d_scaling/40n/dipper_0_015B_core_256_d_scaling_40n_step_1970.ckpt} RENAMED
File without changes
checkpoints/{dipper_15m/core/d_scaling/bin256/80n/dipper_15m_core_bin256_d_scaling_80n_step_3938.ckpt → 0_015B/core/256_d_scaling/80n/dipper_0_015B_core_256_d_scaling_80n_step_3938.ckpt} RENAMED
File without changes
checkpoints/{dipper_15m/core/ws_scaling/bin256/dipper_15m_core_bin256_ws_scaling_step_7875.ckpt → 0_015B/core/256_ws_scaling/dipper_0_015B_core_256_ws_scaling_step_7875.ckpt} RENAMED
File without changes
checkpoints/{dipper_15m/core/d_scaling/bin4096/5n/dipper_15m_core_bin4096_d_scaling_5n_step_248.ckpt → 0_015B/core/4096_d_scaling/05n/dipper_0_015B_core_4096_d_scaling_5n_step_248.ckpt} RENAMED
File without changes
checkpoints/{dipper_15m/core/d_scaling/bin4096/10n/dipper_15m_core_bin4096_d_scaling_10n_step_494.ckpt → 0_015B/core/4096_d_scaling/10n/dipper_0_015B_core_4096_d_scaling_10n_step_494.ckpt} RENAMED
File without changes
checkpoints/{dipper_15m/core/d_scaling/bin4096/20n/dipper_15m_core_bin4096_d_scaling_20n_step_986.ckpt → 0_015B/core/4096_d_scaling/20n/dipper_0_015B_core_4096_d_scaling_20n_step_986.ckpt} RENAMED
File without changes
checkpoints/{dipper_15m/core/d_scaling/bin4096/40n/dipper_15m_core_bin4096_d_scaling_40n_step_1970.ckpt → 0_015B/core/4096_d_scaling/40n/dipper_0_015B_core_4096_d_scaling_40n_step_1970.ckpt} RENAMED
File without changes
checkpoints/{dipper_15m/core/d_scaling/bin4096/80n/dipper_15m_core_bin4096_d_scaling_80n_step_3938.ckpt → 0_015B/core/4096_d_scaling/80n/dipper_0_015B_core_4096_d_scaling_80n_step_3938.ckpt} RENAMED
File without changes
checkpoints/{dipper_15m/core/ws_scaling/bin4096/dipper_15m_core_bin4096_ws_scaling_step_7875.ckpt → 0_015B/core/4096_ws_scaling/dipper_0_015B_core_4096_ws_scaling_step_7875.ckpt} RENAMED
File without changes
checkpoints/{dipper_15m/core/d_scaling/bin65537/5n/dipper_15m_core_bin65537_d_scaling_5n_step_594.ckpt → 0_015B/core/65537_d_scaling/05n/dipper_0_015B_core_65537_d_scaling_5n_step_594.ckpt} RENAMED
File without changes
checkpoints/{dipper_15m/core/d_scaling/bin65537/10n/dipper_15m_core_bin65537_d_scaling_10n_step_1188.ckpt → 0_015B/core/65537_d_scaling/10n/dipper_0_015B_core_65537_d_scaling_10n_step_1188.ckpt} RENAMED
File without changes
checkpoints/{dipper_15m/core/d_scaling/bin65537/20n/dipper_15m_core_bin65537_d_scaling_20n_step_2376.ckpt → 0_015B/core/65537_d_scaling/20n/dipper_0_015B_core_65537_d_scaling_20n_step_2376.ckpt} RENAMED
File without changes
checkpoints/{dipper_15m/core/d_scaling/bin65537/40n/dipper_15m_core_bin65537_d_scaling_40n_step_4752.ckpt → 0_015B/core/65537_d_scaling/40n/dipper_0_015B_core_65537_d_scaling_40n_step_4752.ckpt} RENAMED
File without changes
checkpoints/{dipper_15m/core/d_scaling/bin65537/80n/dipper_15m_core_bin65537_d_scaling_80n_step_9504.ckpt → 0_015B/core/65537_d_scaling/80n/dipper_0_015B_core_65537_d_scaling_80n_step_9504.ckpt} RENAMED
File without changes
checkpoints/{dipper_15m/core/ws_scaling/bin65537/dipper_15m_core_bin65537_ws_scaling_step_19008.ckpt → 0_015B/core/65537_ws_scaling/dipper_0_015B_core_65537_ws_scaling_step_19008.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/d_scaling/qwen3_1_7b_d_scaling_10k_step_12000.ckpt → 1_7B/qwen/d_scaling/dipper_1_7B_qwen_d_scaling_10k_step_12000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/d_scaling/qwen3_1_7b_d_scaling_160k_step_192000.ckpt → 1_7B/qwen/d_scaling/dipper_1_7B_qwen_d_scaling_160k_step_192000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/d_scaling/qwen3_1_7b_d_scaling_20k_step_24000.ckpt → 1_7B/qwen/d_scaling/dipper_1_7B_qwen_d_scaling_20k_step_24000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/d_scaling/qwen3_1_7b_d_scaling_40k_step_48000.ckpt → 1_7B/qwen/d_scaling/dipper_1_7B_qwen_d_scaling_40k_step_48000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/d_scaling/qwen3_1_7b_d_scaling_80k_step_96000.ckpt → 1_7B/qwen/d_scaling/dipper_1_7B_qwen_d_scaling_80k_step_96000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/freesolv/qwen3_1_7b_freesolv_step_10000.ckpt → 1_7B/qwen/freesolv/dipper_1_7B_qwen_freesolv_step_10000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/freesolv/qwen3_1_7b_freesolv_step_135000.ckpt → 1_7B/qwen/freesolv/dipper_1_7B_qwen_freesolv_step_135000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/freesolv/qwen3_1_7b_freesolv_step_20000.ckpt → 1_7B/qwen/freesolv/dipper_1_7B_qwen_freesolv_step_20000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/freesolv/qwen3_1_7b_freesolv_step_40000.ckpt → 1_7B/qwen/freesolv/dipper_1_7B_qwen_freesolv_step_40000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/freesolv/qwen3_1_7b_freesolv_step_5000.ckpt → 1_7B/qwen/freesolv/dipper_1_7B_qwen_freesolv_step_5000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/freesolv/qwen3_1_7b_freesolv_step_80000.ckpt → 1_7B/qwen/freesolv/dipper_1_7B_qwen_freesolv_step_80000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/implicit/01f45245_5557923_step_30000.ckpt → 1_7B/qwen/implicit/dipper_1_7B_qwen_implicit_01f45245_5557923_step_30000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/implicit/01f45245_5557923_step_35000.ckpt → 1_7B/qwen/implicit/dipper_1_7B_qwen_implicit_01f45245_5557923_step_35000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/implicit/01f45245_5557923_step_40000.ckpt → 1_7B/qwen/implicit/dipper_1_7B_qwen_implicit_01f45245_5557923_step_40000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/scaling/qwen3_1_7b_ws_scaling_step_10000.ckpt → 1_7B/qwen/ws_scaling/dipper_1_7B_qwen_ws_scaling_step_10000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/scaling/qwen3_1_7b_ws_scaling_step_20000.ckpt → 1_7B/qwen/ws_scaling/dipper_1_7B_qwen_ws_scaling_step_20000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/scaling/qwen3_1_7b_ws_scaling_step_40000.ckpt → 1_7B/qwen/ws_scaling/dipper_1_7B_qwen_ws_scaling_step_40000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/scaling/qwen3_1_7b_ws_scaling_step_5000.ckpt → 1_7B/qwen/ws_scaling/dipper_1_7B_qwen_ws_scaling_step_5000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/scaling/qwen3_1_7b_ws_scaling_step_80000.ckpt → 1_7B/qwen/ws_scaling/dipper_1_7B_qwen_ws_scaling_step_80000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/scaling_rescue/qwen3_1_7b_ws_scaling_rescue_step_160000.ckpt → 1_7B/qwen/ws_scaling_rescue/dipper_1_7B_qwen_ws_scaling_rescue_step_160000.ckpt} RENAMED
File without changes