Uh oh!
There was an error while loading.Please reload this page.
- Notifications
You must be signed in to change notification settings - Fork4.1k
Pull requests: unslothai/unsloth
Author
Uh oh!
There was an error while loading.Please reload this page.
Label
Uh oh!
There was an error while loading.Please reload this page.
Projects
Uh oh!
There was an error while loading.Please reload this page.
Milestones
Uh oh!
There was an error while loading.Please reload this page.
Reviews
Assignee
Assigned to nobodyLoading
Uh oh!
There was an error while loading.Please reload this page.
Sort
Pull requests list
add FastSentenceTransformer for easily finetuning SentenceTransformer models
#3719 openedDec 12, 2025 byelectroglyphLoading…
Add
target_parameters support for MoE models and fix trainer bugs #3708 openedDec 10, 2025 byOEvortexLoading…
Fix: Support past_key_values in model.generate for multi-turn conversations
#3653 openedNov 29, 2025 byvivekkalyanarangan30Loading…
4 tasks done
Chunk Across Batch and Context length for logprob calculations for grpo
#3628 openedNov 21, 2025 bypluescluesLoading…
Add Qwen2.5 Coder model support to registry and chat templates
#3436 openedOct 11, 2025 bySamama-IntellixcoreLoading…
Phi‑2 support: partial RoPE, deterministic dropout, loader dispatch, and smoke test
#3125 openedAug 9, 2025 byMagellaXLoading…
fix(issue 2950): properly handle spaces in file paths when invoking commands
#2951 openedJul 13, 2025 bydetjonmatajLoading…
Fix llama.cpp quantize location and execution on Windows.
#2894 openedJul 7, 2025 bysimpolismLoading…
Avoid materializing the entire logit matrix for logp calculations.
#2772 openedJun 19, 2025 byzkpranavLoading…
ProTip! Mix and match filters to narrow down what you’re looking for.