Merged
Conversation
ngxson
commented
Feb 16, 2026
convert_hf_to_gguf.py
Outdated
| n_kv_head = self.hparams["num_key_value_heads"] | ||
| n_embd = self.hparams["hidden_size"] | ||
| head_dim = n_embd // n_head | ||
| head_dim = self.hparams["head_dim"] |
Collaborator
Author
There was a problem hiding this comment.
Alright, seems like the existing GGUF is already broken out-of-the-box since #18042 , mostly due to this wrong head_dim calculation. Need to do more testing...
Collaborator
Author
There was a problem hiding this comment.
Confirmed, this PR fixes the quality problem from the original PR #18042
CISC
approved these changes
Feb 17, 2026
This comment was marked as spam.
This comment was marked as spam.
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
liparetejas
pushed a commit
to liparetejas/llama.cpp
that referenced
this pull request
Feb 23, 2026
* model: support GLM-OCR * Update convert_hf_to_gguf.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
bartowski1182
pushed a commit
to bartowski1182/llama.cpp
that referenced
this pull request
Mar 2, 2026
* model: support GLM-OCR * Update convert_hf_to_gguf.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
ArberSephirotheca
pushed a commit
to ArberSephirotheca/llama.cpp
that referenced
this pull request
Mar 3, 2026
* model: support GLM-OCR * Update convert_hf_to_gguf.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
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
3 participants
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.
Fix #19335
Target support https://huggingface.co/zai-org/GLM-OCR
The model is just GLM4V under the hood with some additional features (see below), the transformers code already reflected most of the differences:
GGUF: to be uploaded...