Hugging Face's logo

niklastr
/
dipper

Model card Files
xet
 Community
niklastr commited on
Commit
32d1716
·
verified ·
1 Parent(s): 418573a

Normalize DIPPER checkpoint layout

Browse files
Files changed (40) hide show
  1. checkpoints/0_008B/core/{256_d_scaling → 00256_d_scaling}/05n/dipper_0_008B_core_256_d_scaling_5n_step_137.ckpt +0 -0
  2. checkpoints/0_008B/core/{256_d_scaling → 00256_d_scaling}/10n/dipper_0_008B_core_256_d_scaling_10n_step_273.ckpt +0 -0
  3. checkpoints/0_008B/core/{256_d_scaling → 00256_d_scaling}/20n/dipper_0_008B_core_256_d_scaling_20n_step_545.ckpt +0 -0
  4. checkpoints/0_008B/core/{256_d_scaling → 00256_d_scaling}/40n/dipper_0_008B_core_256_d_scaling_40n_step_1089.ckpt +0 -0
  5. checkpoints/0_008B/core/{256_d_scaling → 00256_d_scaling}/80n/dipper_0_008B_core_256_d_scaling_80n_step_2177.ckpt +0 -0
  6. checkpoints/0_015B/core/{256_d_scaling → 00256_d_scaling}/05n/dipper_0_015B_core_256_d_scaling_5n_step_248.ckpt +0 -0
  7. checkpoints/0_015B/core/{256_d_scaling → 00256_d_scaling}/10n/dipper_0_015B_core_256_d_scaling_10n_step_494.ckpt +0 -0
  8. checkpoints/0_015B/core/{256_d_scaling → 00256_d_scaling}/20n/dipper_0_015B_core_256_d_scaling_20n_step_986.ckpt +0 -0
  9. checkpoints/0_015B/core/{256_d_scaling → 00256_d_scaling}/40n/dipper_0_015B_core_256_d_scaling_40n_step_1970.ckpt +0 -0
  10. checkpoints/0_015B/core/{256_d_scaling → 00256_d_scaling}/80n/dipper_0_015B_core_256_d_scaling_80n_step_3938.ckpt +0 -0
  11. checkpoints/0_030B/core/{256_d_scaling → 00256_d_scaling}/05n/dipper_0_030B_core_256_d_scaling_5n_step_984.ckpt +0 -0
  12. checkpoints/0_030B/core/{256_d_scaling → 00256_d_scaling}/10n/dipper_0_030B_core_256_d_scaling_10n_step_1968.ckpt +0 -0
  13. checkpoints/0_030B/core/{256_d_scaling → 00256_d_scaling}/20n/dipper_0_030B_core_256_d_scaling_20n_step_3935.ckpt +0 -0
  14. checkpoints/0_030B/core/{256_d_scaling → 00256_d_scaling}/40n/dipper_0_030B_core_256_d_scaling_40n_step_7870.ckpt +0 -0
  15. checkpoints/0_030B/core/{256_d_scaling → 00256_d_scaling}/80n/dipper_0_030B_core_256_d_scaling_80n_step_15738.ckpt +0 -0
  16. checkpoints/0_049B/core/{256_d_scaling → 00256_d_scaling}/05n/dipper_0_049B_core_256_d_scaling_5n_step_1847.ckpt +0 -0
  17. checkpoints/0_049B/core/{256_d_scaling → 00256_d_scaling}/10n/dipper_0_049B_core_256_d_scaling_10n_step_3694.ckpt +0 -0
  18. checkpoints/0_049B/core/{256_d_scaling → 00256_d_scaling}/20n/dipper_0_049B_core_256_d_scaling_20n_step_7386.ckpt +0 -0
  19. checkpoints/0_049B/core/{256_d_scaling → 00256_d_scaling}/40n/dipper_0_049B_core_256_d_scaling_40n_step_14771.ckpt +0 -0
  20. checkpoints/0_049B/core/{256_d_scaling → 00256_d_scaling}/80n/dipper_0_049B_core_256_d_scaling_80n_step_29541.ckpt +0 -0
  21. checkpoints/0_085B/core/{256_d_scaling → 00256_d_scaling}/05n/dipper_0_085B_core_256_d_scaling_5n_step_4497.ckpt +0 -0
  22. checkpoints/0_085B/core/{256_d_scaling → 00256_d_scaling}/10n/dipper_0_085B_core_256_d_scaling_10n_step_8993.ckpt +0 -0
  23. checkpoints/0_085B/core/{256_d_scaling → 00256_d_scaling}/20n/dipper_0_085B_core_256_d_scaling_20n_step_17986.ckpt +0 -0
  24. checkpoints/0_085B/core/{256_d_scaling → 00256_d_scaling}/40n/dipper_0_085B_core_256_d_scaling_40n_step_35970.ckpt +0 -0
  25. checkpoints/0_085B/core/{256_d_scaling → 00256_d_scaling}/80n/dipper_0_085B_core_256_d_scaling_80n_step_71940.ckpt +0 -0
  26. checkpoints/0_3B/core/{256_d_scaling → 00256_d_scaling}/05n/dipper_0_3B_core_256_d_scaling_5n_step_9299.ckpt +0 -0
  27. checkpoints/0_3B/core/{256_d_scaling → 00256_d_scaling}/10n/dipper_0_3B_core_256_d_scaling_10n_step_18598.ckpt +0 -0
  28. checkpoints/0_3B/core/{256_d_scaling → 00256_d_scaling}/20n/dipper_0_3B_core_256_d_scaling_20n_step_37196.ckpt +0 -0
  29. checkpoints/0_3B/core/{256_d_scaling → 00256_d_scaling}/40n/dipper_0_3B_core_256_d_scaling_40n_step_74390.ckpt +0 -0
  30. checkpoints/0_3B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_3B_qwen_d_scaling_10k_step_12000.ckpt +0 -0
  31. checkpoints/0_3B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_3B_qwen_d_scaling_160k_step_192000.ckpt +0 -0
  32. checkpoints/0_3B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_3B_qwen_d_scaling_20k_step_24000.ckpt +0 -0
  33. checkpoints/0_3B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_3B_qwen_d_scaling_320k_step_384000.ckpt +0 -0
  34. checkpoints/0_3B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_3B_qwen_d_scaling_40k_step_48000.ckpt +0 -0
  35. checkpoints/0_3B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_3B_qwen_d_scaling_80k_step_96000.ckpt +0 -0
  36. checkpoints/0_6B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_6B_qwen_d_scaling_10k_step_12000.ckpt +0 -0
  37. checkpoints/0_6B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_6B_qwen_d_scaling_160k_step_192000.ckpt +0 -0
  38. checkpoints/0_6B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_6B_qwen_d_scaling_20k_step_24000.ckpt +0 -0
  39. checkpoints/0_6B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_6B_qwen_d_scaling_320k_step_384000.ckpt +0 -0
  40. checkpoints/0_6B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_6B_qwen_d_scaling_40k_step_48000.ckpt +0 -0
checkpoints/0_008B/core/{256_d_scaling → 00256_d_scaling}/05n/dipper_0_008B_core_256_d_scaling_5n_step_137.ckpt RENAMED
File without changes
checkpoints/0_008B/core/{256_d_scaling → 00256_d_scaling}/10n/dipper_0_008B_core_256_d_scaling_10n_step_273.ckpt RENAMED
File without changes
checkpoints/0_008B/core/{256_d_scaling → 00256_d_scaling}/20n/dipper_0_008B_core_256_d_scaling_20n_step_545.ckpt RENAMED
File without changes
checkpoints/0_008B/core/{256_d_scaling → 00256_d_scaling}/40n/dipper_0_008B_core_256_d_scaling_40n_step_1089.ckpt RENAMED
File without changes
checkpoints/0_008B/core/{256_d_scaling → 00256_d_scaling}/80n/dipper_0_008B_core_256_d_scaling_80n_step_2177.ckpt RENAMED
File without changes
checkpoints/0_015B/core/{256_d_scaling → 00256_d_scaling}/05n/dipper_0_015B_core_256_d_scaling_5n_step_248.ckpt RENAMED
File without changes
checkpoints/0_015B/core/{256_d_scaling → 00256_d_scaling}/10n/dipper_0_015B_core_256_d_scaling_10n_step_494.ckpt RENAMED
File without changes
checkpoints/0_015B/core/{256_d_scaling → 00256_d_scaling}/20n/dipper_0_015B_core_256_d_scaling_20n_step_986.ckpt RENAMED
File without changes
checkpoints/0_015B/core/{256_d_scaling → 00256_d_scaling}/40n/dipper_0_015B_core_256_d_scaling_40n_step_1970.ckpt RENAMED
File without changes
checkpoints/0_015B/core/{256_d_scaling → 00256_d_scaling}/80n/dipper_0_015B_core_256_d_scaling_80n_step_3938.ckpt RENAMED
File without changes
checkpoints/0_030B/core/{256_d_scaling → 00256_d_scaling}/05n/dipper_0_030B_core_256_d_scaling_5n_step_984.ckpt RENAMED
File without changes
checkpoints/0_030B/core/{256_d_scaling → 00256_d_scaling}/10n/dipper_0_030B_core_256_d_scaling_10n_step_1968.ckpt RENAMED
File without changes
checkpoints/0_030B/core/{256_d_scaling → 00256_d_scaling}/20n/dipper_0_030B_core_256_d_scaling_20n_step_3935.ckpt RENAMED
File without changes
checkpoints/0_030B/core/{256_d_scaling → 00256_d_scaling}/40n/dipper_0_030B_core_256_d_scaling_40n_step_7870.ckpt RENAMED
File without changes
checkpoints/0_030B/core/{256_d_scaling → 00256_d_scaling}/80n/dipper_0_030B_core_256_d_scaling_80n_step_15738.ckpt RENAMED
File without changes
checkpoints/0_049B/core/{256_d_scaling → 00256_d_scaling}/05n/dipper_0_049B_core_256_d_scaling_5n_step_1847.ckpt RENAMED
File without changes
checkpoints/0_049B/core/{256_d_scaling → 00256_d_scaling}/10n/dipper_0_049B_core_256_d_scaling_10n_step_3694.ckpt RENAMED
File without changes
checkpoints/0_049B/core/{256_d_scaling → 00256_d_scaling}/20n/dipper_0_049B_core_256_d_scaling_20n_step_7386.ckpt RENAMED
File without changes
checkpoints/0_049B/core/{256_d_scaling → 00256_d_scaling}/40n/dipper_0_049B_core_256_d_scaling_40n_step_14771.ckpt RENAMED
File without changes
checkpoints/0_049B/core/{256_d_scaling → 00256_d_scaling}/80n/dipper_0_049B_core_256_d_scaling_80n_step_29541.ckpt RENAMED
File without changes
checkpoints/0_085B/core/{256_d_scaling → 00256_d_scaling}/05n/dipper_0_085B_core_256_d_scaling_5n_step_4497.ckpt RENAMED
File without changes
checkpoints/0_085B/core/{256_d_scaling → 00256_d_scaling}/10n/dipper_0_085B_core_256_d_scaling_10n_step_8993.ckpt RENAMED
File without changes
checkpoints/0_085B/core/{256_d_scaling → 00256_d_scaling}/20n/dipper_0_085B_core_256_d_scaling_20n_step_17986.ckpt RENAMED
File without changes
checkpoints/0_085B/core/{256_d_scaling → 00256_d_scaling}/40n/dipper_0_085B_core_256_d_scaling_40n_step_35970.ckpt RENAMED
File without changes
checkpoints/0_085B/core/{256_d_scaling → 00256_d_scaling}/80n/dipper_0_085B_core_256_d_scaling_80n_step_71940.ckpt RENAMED
File without changes
checkpoints/0_3B/core/{256_d_scaling → 00256_d_scaling}/05n/dipper_0_3B_core_256_d_scaling_5n_step_9299.ckpt RENAMED
File without changes
checkpoints/0_3B/core/{256_d_scaling → 00256_d_scaling}/10n/dipper_0_3B_core_256_d_scaling_10n_step_18598.ckpt RENAMED
File without changes
checkpoints/0_3B/core/{256_d_scaling → 00256_d_scaling}/20n/dipper_0_3B_core_256_d_scaling_20n_step_37196.ckpt RENAMED
File without changes
checkpoints/0_3B/core/{256_d_scaling → 00256_d_scaling}/40n/dipper_0_3B_core_256_d_scaling_40n_step_74390.ckpt RENAMED
File without changes
checkpoints/0_3B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_3B_qwen_d_scaling_10k_step_12000.ckpt RENAMED
File without changes
checkpoints/0_3B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_3B_qwen_d_scaling_160k_step_192000.ckpt RENAMED
File without changes
checkpoints/0_3B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_3B_qwen_d_scaling_20k_step_24000.ckpt RENAMED
File without changes
checkpoints/0_3B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_3B_qwen_d_scaling_320k_step_384000.ckpt RENAMED
File without changes
checkpoints/0_3B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_3B_qwen_d_scaling_40k_step_48000.ckpt RENAMED
File without changes
checkpoints/0_3B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_3B_qwen_d_scaling_80k_step_96000.ckpt RENAMED
File without changes
checkpoints/0_6B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_6B_qwen_d_scaling_10k_step_12000.ckpt RENAMED
File without changes
checkpoints/0_6B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_6B_qwen_d_scaling_160k_step_192000.ckpt RENAMED
File without changes
checkpoints/0_6B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_6B_qwen_d_scaling_20k_step_24000.ckpt RENAMED
File without changes
checkpoints/0_6B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_6B_qwen_d_scaling_320k_step_384000.ckpt RENAMED
File without changes
checkpoints/0_6B/qwen/{d_scaling → 4096_d_scaling}/dipper_0_6B_qwen_d_scaling_40k_step_48000.ckpt RENAMED
File without changes