models: new MPT model file without duplicated token_embd.weight #2006
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Outdated suggestions cannot be applied.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.
Building on ggerganov/llama.cpp#4978 and ggerganov/llama.cpp#5650, I was finally able to implement a version of ggerganov/llama.cpp#3626 that upstream was satisfied by in ggerganov/llama.cpp#5670.
Now MPT Chat has gone from 3.64 GiB to 3.54 GiB on disk, without breaking upstream compatibility in either direction.