Add K-EXAONE MoE#719
Merged
Merged
Conversation
# Conflicts: # tests/test_models.py
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 for issue #718 :)
Model: https://huggingface.co/LGAI-EXAONE/K-EXAONE-236B-A23B
Note
The probability of
</think>gets significantly reduced on 4-bit (see table below), resulting in very long reasoning chains. I've tried to adjust the layer quantization, but wasn't able to find a silver bullet to the issue. I'd recommend sticking to 5-bit or above for now.</think>probabilityBut</think></think></think>Benchmark
Mac Studio M3 Ultra, 512 prompt tokens, 1024 generation tokens
Generation