unsloth/unsloth
Datta Nimmaturi 015fa5772a
Clear MRoPE after generation for GRPO (#5683)
* clear mrope state after generation

* move clear mrope to here

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
2026-05-27 07:32:20 -07:00
..
dataprep fix(loader): honour HF_HUB_OFFLINE / TRANSFORMERS_OFFLINE in from_pretrained (#5598) 2026-05-19 01:05:13 -07:00
kernels Fix loss function not patched for Qwen3.5 models (#5442) 2026-05-19 03:57:50 -07:00
models Clear MRoPE after generation for GRPO (#5683) 2026-05-27 07:32:20 -07:00
optimizers feat: Implement Q-GaLore optimizer and custom embedding learning rate… (#4511) 2026-03-25 01:03:10 -07:00
registry Revert "[pre-commit.ci] auto fixes from pre-commit.com hooks" 2025-12-01 07:24:58 -08:00
utils Add check to disable xformers on newer GPUs (#4342) 2026-03-16 22:42:38 -07:00
__init__.py MLX training support for Studio on Apple Silicon (#5340) 2026-05-14 05:24:20 -07:00
_auto_install.py Add PyTorch 2.10 and xformers 0.0.34 support (#3985) 2026-02-05 05:56:26 -08:00
_gpu_init.py Versioning 2026-05-18 05:29:52 -07:00
chat_templates.py fix(chat_templates): check find() return value before slicing on placeholders (#5763) 2026-05-25 06:19:01 -07:00
device_type.py revert: stop touching DEVICE_TYPE == "cuda" branches for CPU CI (#5473) 2026-05-15 19:41:09 -07:00
import_fixes.py disable_torchcodec_if_broken: also patch datasets and clean sys.modules (#5483) 2026-05-16 16:24:48 -07:00
ollama_template_mappers.py Re-apply #4939: updated models template mappers (#4950) 2026-04-15 07:52:12 -07:00
save.py fix: preserve tokenizer eos token on merged saves (#5451) 2026-05-17 06:44:23 -07:00
tokenizer_utils.py fix: 3 patch_* helpers — fast_lora import, sft_trainer Union, openenv OSError (#5319) 2026-05-07 00:12:09 -07:00
trainer.py Trim trainer.py import-fix comment to one line 2026-05-06 07:22:56 +00:00