FEAT: Support RWKV Pile #535
Draft
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
|
It seems that all the tests are actually passing, but somehow there is a segmentation fault from Stable Diffusion test. Not sure if this is just a probabilistic error or do I need to fix something. |
|
Hi, could you please also update the docs? Here's an example: #587 |
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Outdated suggestions cannot be applied.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.
Resolve #533
Add support for rwkv-4-pile models. Successfully tested the 169m variant on a local Mac setup.
I would like some guidance on setting the model size. Historically, we've rounded up the sizes for models with parameters fewer than 1 billion. However, with rwkv-4-pile, we encounter two smaller models: 169m and 430m.
I am leaning towards simply excluding the 169m variant and setting the smallest size threshold at 430m (for 1b). However, alternative suggestions are welcomed.