Skip to content

Pull requests: TransformerLensOrg/TransformerLens

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
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

Add DeepSeek V4 architecture adapter
#1513 opened Jul 13, 2026 by abhinav-bellapu Contributor Draft
7 tasks done
Add forward-only LLaDA architecture adapter
#1512 opened Jul 12, 2026 by hsusul Contributor Loading…
Add Lfm2 support
#1510 opened Jul 12, 2026 by TensorCruncher Contributor Loading…
1 task done
Keep input_tokens on the model device in generate()
#1509 opened Jul 11, 2026 by danielxmed Loading…
6 of 7 tasks
Add from scratch pretrain converter
#1506 opened Jul 11, 2026 by Cacapice Loading…
Add Apertus adapter tests and fix nested key translation
#1503 opened Jul 11, 2026 by abhinav-bellapu Contributor Loading…
Fix 4-bit split QKV projection
#1502 opened Jul 10, 2026 by abhinav-bellapu Contributor Loading…
Fix n_devices max_memory caps
#1501 opened Jul 10, 2026 by abhinav-bellapu Contributor Loading…
Add OLMo 3 base model aliases
#1500 opened Jul 10, 2026 by abhinav-bellapu Contributor Loading…
6 of 7 tasks
add t5gemma2 adapter and tests
#1495 opened Jul 9, 2026 by zinichakraborty Loading…
6 of 7 tasks
fix: migrate jupyter dependency group to Notebook 7
#1494 opened Jul 8, 2026 by chandrudp29 Contributor Loading…
10 tasks
Added HRM-Text two-timescale recurrent adapter
#1487 opened Jul 6, 2026 by MdSadiqMd Contributor Loading…
8 of 10 tasks
Add AST (Audio Spectrogram Transformer) Adapter
#1484 opened Jul 3, 2026 by dylanberens Loading…
6 tasks done
ProTip! Follow long discussions with comments:>50.