[GGUF] Parse Quant Label #967
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
mishig25
force-pushed
the
parse_quant_label
branch
from
8daee6b to
bec0439
Compare
Merged
ngxson
reviewed
Oct 16, 2024
| expect(parseGGUFQuantLabel("subdir/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf")).toEqual("Q4_K_M"); | ||
| expect(parseGGUFQuantLabel("Codestral-22B-v0.1-Q2_K.gguf")).toEqual("Q2_K"); | ||
| expect(parseGGUFQuantLabel("Codestral-22B-v0.1gguf")).toEqual(undefined); | ||
| expect(parseGGUFQuantLabel("Codestral-22B-v0.1-F32-Q2_K.gguf")).toEqual("Q2_K"); // gguf name with two quant labels [F32, Q2_K] |
Member
There was a problem hiding this comment.
Some interesting test cases that can be added:
Suggested change
| expect(parseGGUFQuantLabel("Codestral-22B-v0.1-F32-Q2_K.gguf")).toEqual("Q2_K"); // gguf name with two quant labels [F32, Q2_K] | |
| expect(parseGGUFQuantLabel("Codestral-22B-v0.1-F32-Q2_K.gguf")).toEqual("Q2_K"); // gguf name with two quant labels [F32, Q2_K] | |
| expect(parseGGUFQuantLabel("Codestral-22B-v0.1-IQ3_XS.gguf")).toEqual("IQ3_XS"); | |
| expect(parseGGUFQuantLabel("Codestral-22B-v0.1-Q4_0_4_4.gguf")).toEqual("Q4_0_4_4"); |
Collaborator
Author
There was a problem hiding this comment.
I had to push ed2a0df
because parseGGUFQuantLabel is based on what's typed in enum ggml_type. And IQ3_XS , Q4_0_4_4 does not exist in enum ggml_type atm. However, I do see that Codestral-22B-v0.1-IQ3_XS.gguf is on the hub. I'd say: we should merge this PR and try to handle these edge cases in subseq PR
Member
There was a problem hiding this comment.
ok no problem for me, AFAIK not many users use the Q4_0_4_4 stuff-
Co-authored-by: Xuan Son Nguyen <[email protected]>
ngxson
approved these changes
Oct 16, 2024
julien-c
reviewed
Oct 16, 2024
Co-authored-by: Julien Chaumond <[email protected]>
julien-c
approved these changes
Oct 16, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Moving this function from moon to hf.js/gguf as I need it for #687
Order of operations
@hf.js/gguf@hf.js/tasks