Make a few GLM tensors not required (to support GLM 4.6) #16359
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
layer.nextn.shared_head_head and layer.nextn.embed_tokens are both excluded from GLM 4.6 resulting in the model not loading after conversion/quantization, this marks those tensors as not required which makes it work
bartowski1182
changed the title
CISC
approved these changes
Sep 30, 2025
|
Life's too short for CIs (I checked locally). :) |
|
Thanks CISC! <3 |
4 tasks
1 task
yael-works
pushed a commit
to yael-works/llama.cpp
that referenced
this pull request
Oct 15, 2025
…gml-org#16359) * Make a few GLM tensors not required layer.nextn.shared_head_head and layer.nextn.embed_tokens are both excluded from GLM 4.6 resulting in the model not loading after conversion/quantization, this marks those tensors as not required which makes it work * Update llama-model.cpp layer.nextn.shared_head_norm also not required in case of future models
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
layer.nextn.shared_head_head and layer.nextn.embed_tokens are both excluded from GLM 4.6 resulting in the model not loading after conversion/quantization, this marks those tensors as not required which makes it work
Before this change I got
llama_model_load: error loading model: missing tensor 'blk.92.nextn.embed_tokens.weight'With this change the model loads and runs successfully
Thanks compilade for pointing in the right direction
Workaround for conversion should anyone else come across this:
convert_hf_to_gguf.py currently only looks at model*.safetensor files
if you rename
mtp.safetensorstomodel-mtp.safetensorsit will work properlyMake sure to read the contributing guidelines before submitting a PR