Improvement to enable quantization of Merge Models #623
Conversation
This file contains 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
Fixes inf and nan values in the tensors that happen in the models produced by the merge of others. In those cases the inf values are replaced by MAX_VALUE.
Readme changes reverted
|
I think this would be redundant with some of the recent changes. I don't like simply suppressing errors in the reference state, but I've added a check that allows for clamping +/- inf values if they make up a very small portion of the state. |
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Outdated suggestions cannot be applied.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.
Fixes Inf and NaN values in the tensors that happen in the models produced by the merge of others. In those cases the inf values are replaced by MAX_VALUE.
I have successfully tested it in the quantization of invisietch/Nimbus-Miqu-v0.1-70B.