Simplify #525
Merged
Simplify #525
Conversation
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
…gym_eval_strategies
Add position_ids back in so that sequence packing with flash attention works. Add shorter example fasta for generation tests Keep insertions for scoring and generation
alex-hh
reviewed
Dec 16, 2025
alex-hh
reviewed
Dec 16, 2025
alex-hh
approved these changes
Dec 16, 2025
Owner
alex-hh
left a comment
alex-hh
left a comment
There was a problem hiding this comment.
Let's merge whenever you're happy and go from there (I copied current master branch to a new dev branch for now).
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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Outdated suggestions cannot be applied.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.
This PR strips back the repo to the core functionality required for the preprint version of the model.
Only (sequence only) text memmap datasets are supported for training.
Inference is supported with the following entry-point scripts:
scripts/generate_sequences.py
scripts/score_sequences.py
Training configs are provided for reproducing the preprint version of the model and a training config using example data and a recommended training config for training a model using the profam atlas dataset.