Fix model architecture name case mismatch breaking TL2 conversion#401
Open
Ayush10 wants to merge 1 commit intomicrosoft:mainfrom
Open
Fix model architecture name case mismatch breaking TL2 conversion#401Ayush10 wants to merge 1 commit intomicrosoft:mainfrom
Ayush10 wants to merge 1 commit intomicrosoft:mainfrom
Conversation
The model registration decorator used "BitnetForCausalLM" (lowercase 'n') but HuggingFace model configs specify "BitNetForCausalLM" (uppercase 'N'). This caused a NotImplementedError when converting models to TL2 GGUF format, since the case-sensitive dictionary lookup in from_model_architecture() failed. Fixed in both convert-hf-to-gguf-bitnet.py and generate-dummy-bitnet-model.py. Fixes microsoft#300
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
@Model.register("BitnetForCausalLM")→@Model.register("BitNetForCausalLM")(capital 'N') in bothconvert-hf-to-gguf-bitnet.pyandgenerate-dummy-bitnet-model.py"BitNetForCausalLM"as the architecture name, but the registration decorator had a lowercase 'n', causing the case-sensitive lookup infrom_model_architecture()to fail withNotImplementedError: Architecture 'BitNetForCausalLM' not supported!python setup_env.py -md models/BitNet-b1.58-2B-4T -q tl2)Test plan
python setup_env.py -md models/BitNet-b1.58-2B-4T -q tl2and verify conversion completes withoutNotImplementedErrori2_sandtl1quantization paths still workFixes #300