-
Notifications
You must be signed in to change notification settings - Fork 319
Pull requests: thinking-machines-lab/tinker-cookbook
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Support Qwen3VL in merge_tinker_adapter_to_hf_model
#360
opened Feb 10, 2026 by
opherlieber
Loading…
fix: normalize SFT weights per-example for consistent gradient magnitudes
#334
opened Jan 31, 2026 by
bledden
Loading…
6 of 7 tasks
feat: Add Harbor terminal RL recipe + tinker-cookbook Env adapter
#321
opened Jan 22, 2026 by
tyfeng1997
Loading…
Add .python-version and uv.lock for Python 3.12
#290
opened Jan 6, 2026 by
ajtejankar
Loading…
1 task done
feat(rl): Filter incomplete trajectories that hit max_tokens limit
#160
opened Dec 10, 2025 by
EvanZhuang
Loading…
[tinker-cookbook] rl: avoid hanging in async runs when we run out of data
#107
opened Nov 22, 2025 by
kennyyu
Loading…
ProTip!
Follow long discussions with comments:>50.