-
Notifications
You must be signed in to change notification settings - Fork 55
Chunking #409
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
Draft
josephdviviano
wants to merge
35
commits into
master
Choose a base branch
from
chunking
base: master
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Draft
Chunking #409
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
…or logic, recurrent estimators, recurrent modules
…com:GFNOrg/torchgfn into generalize_samplers
… generalize_samplers
…tion paths. simplified the API of adapters.
tweak of how default preprocessor is defined
…tion, added some useful safeguard assertions, bugfix related to saving estimator_outputs path
Make adapters logic part of estimators via `PolicyMixin`
jaggbow
reviewed
Oct 15, 2025
| device = states_active.device | ||
| mask = torch.zeros(B, N, dtype=torch.bool, device=device) | ||
|
|
||
| for b in range(B): |
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.
I wonder if it's possible to parallelize this.
jaggbow
reviewed
Oct 15, 2025
| non_exit_ids = [i for i in range(env.n_actions) if i != env.exit_token_id] | ||
| seen = set(env.vocab) | ||
| out: set[Hashable] = set() | ||
| while len(out) < n_tokens_to_add and len(out) < 10_000: |
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.
any reason the 10000 is hard coded here?
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.
Description
This is a DRAFT (no working example yet) which adds the core functionality implemented in https://github.com/GFNOrg/Chunk-GFN
I will update this with details when I have a working implementation.
Please see
testing/test_chunking.pyfor working examples of core functionality.