Replies: 13 comments
-
I'm still in the process of finding/converting the 7B and 13B alpaca models to ggml2 I'll then recompute all the hashes with the latest build, and also provide a file with the magic numbers and versions for each. |
Beta Was this translation helpful? Give feedback.
-
the new ggml file format has the version number 1. calling it ggml2 or "v2" is going to cause confusion. the new file format switched the file magic from "ggml" to "ggmf", maybe we should lean into that. |
Beta Was this translation helpful? Give feedback.
-
Some checksums (q4_0 and gptq-4b quantizations, new tokenizer format) e: added more checksums |
Beta Was this translation helpful? Give feedback.
-
I'd trust your checksums for the alpaca models over mine.
|
Beta Was this translation helpful? Give feedback.
-
the problem with the alpaca models is, that there are alot of different once, by different peoples. |
Beta Was this translation helpful? Give feedback.
-
Yes. However we're supporting them, so we need to decide what we can support. |
Beta Was this translation helpful? Give feedback.
-
Upvote for @anzz1's new naming convention for the various model subdirs. |
Beta Was this translation helpful? Give feedback.
-
@anzz1 why is the tokenizer.model duplicated everywhere, afaik there is only 1 |
Beta Was this translation helpful? Give feedback.
-
@Green-Sky Yeah there is only one, i might be thinking ahead too much. 😄 also added some more checksums for gptq-4b models above #374 (comment) |
Beta Was this translation helpful? Give feedback.
-
IMHO, I think we should move the alpaca checksums to a discussion, with a thread for each indiviual model, with source and credits and converted checksums. |
Beta Was this translation helpful? Give feedback.
-
How about an individual That way we have some granularity and it is self-documenting for new users who don't know a llama from an alpaca. |
Beta Was this translation helpful? Give feedback.
-
yes it might be good to differentiate ones as some have short fur and some long and some are more friendly than others. 1 "standard" sum per 1 model type seems to make the most sense. i cant see why they would need to be their own files though, as i'm not big fan of the idea of littering a repo with dozens of files when the same thing can be achieved with dozens of lines in a single file. i agree this should be moved to discussions as it will be a ongoing thing |
Beta Was this translation helpful? Give feedback.
-
alpaca (LoRa?) 30B q4_0 by Pi3141 as of time of writing, uses the old unversioned file format. converted (ggmf v1) sha256sum:
|
Beta Was this translation helpful? Give feedback.
-
Outdated original post for posterity
Originally posted by @anzz1 in #338 (comment)
edit: After converting the models to the new format, I found out that the "v2" hash above is also incorrect.
The sha256 for
./models/alpaca-7B-ggml/ggml-model-q4_0.bin
is supposed to be2fe0cd21df9c235c0d917c14e1b18d2d7320ed5d8abe48545518e96bb4227524
This is now a general discussion about keeping sha256 checksums updated and maybe have some sort of standardisation.
Beta Was this translation helpful? Give feedback.
All reactions