docs : add MTP to GGUF Type slot#1487
Closed
mishig25 wants to merge 3 commits into
Closed
Conversation
Adds `MTP` as a third value for the `Type` slot, alongside `LoRA` and `vocab`, to cover Multi-Token Prediction / speculative-decoding draft modules shipped beside a base model. Updates the validation regex, adds a parse example, and extends the Node.js test cases. Also adds a short non-normative note that `IQ*` quants do not imply imatrix calibration and that the `i1-` prefix used by some publishers (e.g. mradermacher) is a community convention, not part of the spec. Calibration provenance should live in metadata, not the filename.
mishig25
changed the title
Contributor
Author
|
Closed by an unintentional branch rename on my fork — superseded by #1488 with identical changes. |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds
MTPas a third value for theTypeslot (alongsideLoRAandvocab) to cover Multi-Token Prediction / speculative-decoding draft modules shipped beside a base model. Updates the regex in both spots and adds an example + test case.@ggerganov previously OK'd adding
MTP.Open question: the spec puts
TypeafterEncoding, so the canonical form here is…-Q4_K_M-MTP.gguf. Some community releases placeMTPbefore the encoding (…-MTP-Q4_K_M.gguf). Happy to flip if you'd rather match current filenames.