8000 Pull requests · stanford-crfm/levanter · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Pull requests: stanford-crfm/levanter

New pull request New
19 Open 735 Closed
19 Open 735 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Fix ragged paged decode when sequence resumes codex
#1033 opened Jul 4, 2025 by dlwh Loading…
Adding PSGD-QUAD to optimizer collection
#1022 opened Jul 1, 2025 by evanatyourservice Loading…
1
Add dead neuron histograms codex
#1021 opened Jul 1, 2025 by dlwh Loading…
wip Inference
#1016 opened Jun 27, 2025 by dlwh Loading…
Refactor attention mask structure codex
#1004 opened Jun 22, 2025 by dlwh Loading…
Support parameter tags in optimizer weight decay codex
#996 opened Jun 17, 2025 by dlwh Loading…
1
UpcycleLm script
#987 opened Jun 12, 2025 by blahBlahhhJ Loading…
3
Safetensor gcs
#980 opened May 30, 2025 by dlwh • Draft
feat: Add script for automated WandB workspace setup
#976 opened May 25, 2025 by dlwh Loading…
Add basic model sampling/inference support
#972 opened May 23, 2025 by neel04 Loading…
4 tasks
11
[WIP] DPO
#970 opened May 22, 2025 by nikil-ravi • Draft
log when checkpoints happen
#933 opened Apr 2, 2025 by dlwh Loading…
Allow for tokenizers/preprocessors to change batch size
#866 opened Jan 24, 2025 by Aphoh Loading…
6
Fix grad accum when using loss_mask
#842 opened Dec 13, 2024 by Aphoh Loading…
9
Tweaks to Muon branch
#831 opened Dec 4, 2024 by dlwh Loading…
Merging DiVA to Levanter Main
#779 opened Oct 30, 2024 by Helw150 Loading…
17
[WIP] MLM Training Objective
#680 opened Jul 30, 2024 by prady-saligram • Draft
5
[WIP] Implements Roberta Model
#679 opened Jul 30, 2024 by JulienDarve • Draft
22
Use new ResourceEnvs from Haliax
#444 opened Feb 1, 2024 by dlwh Loading…
ProTip! Mix and match filters to narrow down what you’re looking for.
0