1
0
Fork 0

Assembled from URLs hosted at https://huggingface.co/datasets/togethercomputer/RedPajama-Data-1T

Second batch of data

main
Zach Nation 1 year ago
parent 03570ad577
commit 7bf143df64
772 changed files (15 GiB → 38 GiB)
  1. 2
      Makefile
  2. 4
      arxiv/arxiv_023827cd-7ee8-42e6-aa7b-661731f4c70f.jsonl
  3. 4
      arxiv/arxiv_11c659c1-ffbf-4455-abfd-058f6bbf4bb2.jsonl
  4. 4
      arxiv/arxiv_44e19375-3995-4dff-a3b6-8a25247a165c.jsonl
  5. 4
      arxiv/arxiv_50757a42-079b-41ec-bcca-73759faffd62.jsonl
  6. 4
      arxiv/arxiv_580be642-bb73-4d0d-8b5e-f494722934cd.jsonl
  7. 4
      arxiv/arxiv_5a02d9ee-12a0-437d-808f-d26f0eb2012b.jsonl
  8. 4
      arxiv/arxiv_5d8d402b-8277-480a-b5fa-71169726864f.jsonl
  9. 4
      arxiv/arxiv_5ee33ef7-455e-4fd5-9512-c4771dd802c1.jsonl
  10. 4
      arxiv/arxiv_610c82ed-b9ee-449c-83b0-601205f3a74a.jsonl
  11. 4
      arxiv/arxiv_629fe3ca-075f-4663-9b81-b807f3b42bf2.jsonl
  12. 4
      arxiv/arxiv_64e5075e-e87e-4b2a-9e38-e5c102f6f2b1.jsonl
  13. 4
      arxiv/arxiv_65dd2ff6-dae3-4a60-90d3-c3d7349fc92f.jsonl
  14. 4
      arxiv/arxiv_6719ecd2-fe34-4078-a584-320d921cbf6f.jsonl
  15. 4
      arxiv/arxiv_6938ee72-43ee-4ade-8840-151a402383b0.jsonl
  16. 4
      arxiv/arxiv_73241940-66c1-481c-b53a-f5e8b9afe9fa.jsonl
  17. 4
      arxiv/arxiv_751370b5-c7cb-44d8-a039-1468ee6747ab.jsonl
  18. 4
      arxiv/arxiv_75af5d17-5ebb-4460-9f2a-dc9fe880a936.jsonl
  19. 4
      arxiv/arxiv_79d50803-f7d9-4aa8-bf1a-d807980a40c6.jsonl
  20. 4
      arxiv/arxiv_7ea7a996-b1bb-4773-a36a-461dce2de861.jsonl
  21. 4
      arxiv/arxiv_8232f276-9e3f-463a-9350-362de1b501d1.jsonl
  22. 4
      arxiv/arxiv_8509f5a7-64a8-4813-92dc-f6eb53e3aacc.jsonl
  23. 4
      arxiv/arxiv_872b620a-b4fd-45d3-92bc-ff0584447705.jsonl
  24. 4
      arxiv/arxiv_8ede1b71-6846-439a-acba-86a57cfec3d2.jsonl
  25. 4
      arxiv/arxiv_8f74f6ba-1c53-42d5-a3c7-e4ef46a71133.jsonl
  26. 4
      arxiv/arxiv_f141b736-5ce4-4f18-bb29-704227ca4bd1.jsonl
  27. 4
      arxiv/arxiv_f7680c03-70df-4781-a98d-c88695f92f04.jsonl
  28. 4
      arxiv/arxiv_fbc62949-624d-4943-9731-f5c46242ba55.jsonl
  29. 4
      book/book.jsonl
  30. 4
      c4/c4-train.00000-of-01024.jsonl
  31. 4
      c4/c4-train.00001-of-01024.jsonl
  32. 4
      c4/c4-train.00002-of-01024.jsonl
  33. 4
      c4/c4-train.00003-of-01024.jsonl
  34. 4
      c4/c4-train.00005-of-01024.jsonl
  35. 4
      c4/c4-train.00006-of-01024.jsonl
  36. 4
      c4/c4-train.00007-of-01024.jsonl
  37. 4
      c4/c4-train.00008-of-01024.jsonl
  38. 4
      c4/c4-train.00011-of-01024.jsonl
  39. 4
      c4/c4-train.00024-of-01024.jsonl
  40. 4
      c4/c4-train.00025-of-01024.jsonl
  41. 4
      c4/c4-train.00026-of-01024.jsonl
  42. 4
      c4/c4-train.00027-of-01024.jsonl
  43. 4
      c4/c4-train.00029-of-01024.jsonl
  44. 4
      c4/c4-train.00030-of-01024.jsonl
  45. 4
      c4/c4-train.00130-of-01024.jsonl
  46. 4
      c4/c4-train.00131-of-01024.jsonl
  47. 4
      c4/c4-train.00132-of-01024.jsonl
  48. 4
      c4/c4-train.00133-of-01024.jsonl
  49. 4
      c4/c4-train.00134-of-01024.jsonl
  50. 4
      c4/c4-train.00135-of-01024.jsonl
  51. Some files were not shown because too many files have changed in this diff Show More
Loading…
Cancel
Save