Repository navigation
skills: add slice-model - #30677
Merged
Merged
skills: add slice-model#30677
Conversation
github-actions
Bot
added
the
documentation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Overview
Add
slice-modelwhich allows downloading a slice of a given model for local testingFor example, if HF safetensors model is 32B, this script allow slicing just some layers and only download the necessary tensors, resulting in a 1B model that can run locally.
The main benefit of this approach compared to generating a random weight:
config.jsonstays the same (sometimestransformerscan generate different json based on which version is running)Disclosure: I've been already using this technique for testing many models
Requirements