-
Notifications
You must be signed in to change notification settings - Fork 339
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Representation based alignment and merge #199
base: wip-git-rebasin
Are you sure you want to change the base?
Conversation
shamanez
commented
Mar 18, 2024
•
edited by metric-space
edited by metric-space
weight: 1.0 | ||
- model: garage-bAInd/Platypus2-13B | ||
parameters: | ||
density: 0.5 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
There are also some ZipIt related parameters like Alpha and Beta.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Wow, will these modifications help us compute intermediate representations?
mergekit/_data/mappings/a_b.json
Outdated
"start_architectures": ["A"], | ||
"destination_architectures": ["B"], | ||
"weights_mapping":{ | ||
"a" : "d", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
For ZipIt should we add something like intra & inter feature mapping?
Modified `dump_out_features.py` and added `dump_out_sim_metrics.py`
- computation of correlation matrices - computation mo m&u - correlation modification @metric-space --------- Co-authored-by: Luke Meyers <functor.soup@gmail.com>
#251) Make the work more merekit style