Upload folder using huggingface_hub

#1

Upload folder using huggingface_hub

Multi commit ID: 2ac211c5e080ab4f93f07e5d869c4e448b3b5b9a684ff070c54c4b90a3911551

Scheduled commits:

  • Upload 3 file(s) totalling 1.8G (cb5dfe77bc292db3e6c0c82aa49e147abffe4d482eca95e0660eaa1673cb49ff)
  • Upload 1 file(s) totalling 1.1G (98b19ed60d36d7b7f1400fb11b73b20d056e0036b40c4e3fbc266dba2ad5d956)
  • Upload 1 file(s) totalling 1.5G (b4b5db12a7f20c40678ca0116316cb9ceaac3ea0b3a50fa8af095eb5bbf8b7a9)
  • Upload 1 file(s) totalling 1.8G (a58938953b780dd0e7a1745b23d215069ea6c006b1fe905878824299c952ab00)
  • Upload 1 file(s) totalling 1.4G (3832590de20f79829a2efecac4a3e9e465ac6a752350e80e6436ee9dece841f5)
  • Upload 1 file(s) totalling 1.8G (e36be80d3f0bdc09ff2dc3eca6facb41d31fac615161f5f3d39b00504528b3ac)
  • Upload 1 file(s) totalling 1.7G (ddf8e7a805ae4b707b8076756227dec196dca5e00064e73c535196b1e38ab0e6)
  • Upload 1 file(s) totalling 1.5G (13288067310e5db7f111b6f1ccd4bf138f5d684787d9dd3c05c92b5fe5b5b892)
  • Upload 1 file(s) totalling 2.0G (6b7449993829467b62bde0aeabe6212bbe7fbc6946548025db0c5f0421ea647f)
  • Upload 1 file(s) totalling 2.3G (ae37815b5122c05e447b52d2765056335243ac6520b3568f4060bc7aad91d94c)
  • Upload 1 file(s) totalling 2.3G (94335bcbbee8152dd78ad6f413ddcfed59e02fe5c2d9bacc00e0d695e21107b6)
  • Upload 1 file(s) totalling 2.6G (1e477f5397dad392376f3f8f7094a8bc0e8914a2f5186605b12106dc5f0582ee)
  • Upload 1 file(s) totalling 3.4G (5c52f328533dc4e716feaeae014cff9fb805d5fa06f133e8f04168cad5ee8d6b)
  • Upload 1 file(s) totalling 6.4G (9588c40e331fb7c3e4cd10dc51f5ead7c6b58e92945bdf71952b57e20631a61d)
  • Upload 2 file(s) totalling 1.9G (9d30cd7db88a2303555faa38434f58b248a77e8058528b5c328e384b3c091ee3)

This is a PR opened using the huggingface_hub library in the context of a multi-commit. PR can be commented as a usual PR. However, please be aware that manually updating the PR description, changing the PR status, or pushing new commits, is not recommended as it might corrupt the commit process. Learn more about multi-commits in this guide.

MaziyarPanahi changed pull request title from [WIP] Upload folder using huggingface_hub (multi-commit 2ac211c5e080ab4f93f07e5d869c4e448b3b5b9a684ff070c54c4b90a3911551) to Upload folder using huggingface_hub

create_pr=False has been passed so PR is automatically merged.

This is a comment posted using the huggingface_hub library in the context of a multi-commit. Learn more about multi-commits in this guide.

MaziyarPanahi changed pull request status to merged

Multi-commit is now completed! You can ping the repo owner to review the changes. This PR can now be commented or modified without risking to corrupt it.

This is a comment posted using the huggingface_hub library in the context of a multi-commit. Learn more about multi-commits in this guide.

MaziyarPanahi changed pull request status to open

The fp16 version of just a convert, or is a quantization from 16 to 16 with imatrix option?

I have never seen a quantized 16-bit! That option doesn’t exist, if you have enough vram to run 16bit then any quantized would be less of a quality no matter what. (You can’t beat the original model without further training)

Thanks for the answer, that because I cannot do quantization or conversion so I have to use models here in huggingface, since I see that exists the imatrix option, I want to be sure that is not converted or quantized by using that option, thanks a lot.

Sign up or log in to comment