Pyreft

**Full Changelog**: https://github.com/stanfordnlp/pyreft/compare/v0.0.7...v0.0.8

What's Changed
* [P1] Addressing issues in DPO Training (127) by AmirZur in https://github.com/stanfordnlp/pyreft/pull/128
* Debug subspace composition notebook impl by PinetreePantry in https://github.com/stanfordnlp/pyreft/pull/130
* Check in negated reft notebook by PinetreePantry in https://github.com/stanfordnlp/pyreft/pull/131
* [Minor] Update notebook with newer names (132) by frankaging in https://github.com/stanfordnlp/pyreft/pull/133
* [Minor] fix undefined var by frankaging in https://github.com/stanfordnlp/pyreft/pull/134


**Full Changelog**: https://github.com/stanfordnlp/pyreft/compare/v0.0.6...v0.0.7

What's Changed
* [Minor] Update README with an example. by frankaging in https://github.com/stanfordnlp/pyreft/pull/55
* [Minor] Update README with Colab links. by frankaging in https://github.com/stanfordnlp/pyreft/pull/56
* [Minor] Update README by frankaging in https://github.com/stanfordnlp/pyreft/pull/57
* [Major] Support Llama3 models by frankaging in https://github.com/stanfordnlp/pyreft/pull/64
* [Minor] More refactory to support Llama3 experiments by frankaging in https://github.com/stanfordnlp/pyreft/pull/74
* [Minor] fix subspace (72) by frankaging in https://github.com/stanfordnlp/pyreft/pull/75
* ReFT + DPO Tutorial by AmirZur in https://github.com/stanfordnlp/pyreft/pull/76
* Title: Fix: Shape Mismatch during Left Padding Adjustment in compute_metrics (Generated by Ana - AI SDE) by ana-ai-sde in https://github.com/stanfordnlp/pyreft/pull/89
* [P1] support ReFT+PEFT by using ReftModel to wrap PeftModel (46) by frankaging in https://github.com/stanfordnlp/pyreft/pull/93
* [Minor] Enable lora with loreft training by frankaging in https://github.com/stanfordnlp/pyreft/pull/94
* [Minor] Basic support of quantization by frankaging in https://github.com/stanfordnlp/pyreft/pull/100
* [P0] Revert back to ortho init as unstable training by frankaging in https://github.com/stanfordnlp/pyreft/pull/103
* Fix: datasets.exceptions.DatasetNotFoundError when training with alpaca_data_cleaned by savadikarc in https://github.com/stanfordnlp/pyreft/pull/108
* [P0] Fixing LoReFT rotation layer hot loading problem (114) by frankaging in https://github.com/stanfordnlp/pyreft/pull/123

New Contributors
* AmirZur made their first contribution in https://github.com/stanfordnlp/pyreft/pull/76
* ana-ai-sde made their first contribution in https://github.com/stanfordnlp/pyreft/pull/89
* savadikarc made their first contribution in https://github.com/stanfordnlp/pyreft/pull/108

**Full Changelog**: https://github.com/stanfordnlp/pyreft/compare/v0.0.5...v0.0.6

What's Changed
* Fix GitHub links to standfordnlp in the README files by bbrowning in https://github.com/stanfordnlp/pyreft/pull/39
* Update README.md by Vikrant-Khedkar in https://github.com/stanfordnlp/pyreft/pull/47
* Update chat_model.ipynb by Vikrant-Khedkar in https://github.com/stanfordnlp/pyreft/pull/48
* Fix loading IntervenableModel for its subclasses by PinetreePantry in https://github.com/stanfordnlp/pyreft/pull/49
* [Major] Zeta version by aryamanarora in https://github.com/stanfordnlp/pyreft/pull/44

New Contributors
* bbrowning made their first contribution in https://github.com/stanfordnlp/pyreft/pull/39
* Vikrant-Khedkar made their first contribution in https://github.com/stanfordnlp/pyreft/pull/47

**Full Changelog**: https://github.com/stanfordnlp/pyreft/compare/v0.0.4...v0.0.5

What's Changed
* [P0] Fixing the requirements for Kaggle and Google notebooks env by frankaging in https://github.com/stanfordnlp/pyreft/pull/38


**Full Changelog**: https://github.com/stanfordnlp/pyreft/compare/v0.0.3...v0.0.4

Fix requirements.

**Full Changelog**: https://github.com/stanfordnlp/pyreft/compare/v0.0.2...v0.0.3