Pyvene

What's Changed
* [P0] removing seaborn dependency by frankaging in https://github.com/stanfordnlp/pyvene/pull/143


**Full Changelog**: https://github.com/stanfordnlp/pyvene/compare/v0.1.0...v0.1.1

What's Changed
* Zen/update0.0.9 by frankaging in https://github.com/stanfordnlp/pyvene/pull/142


**Full Changelog**: https://github.com/stanfordnlp/pyvene/compare/v0.0.9...v0.1.0

What's Changed
* [Minor] Revert CausalModel to accept input/output functions when generating factual/counterfactual datasets by amirzur2023 in https://github.com/stanfordnlp/pyvene/pull/137
* [P0] Adding back GPT2 and other model supports by frankaging in https://github.com/stanfordnlp/pyvene/pull/139
* [P0] fix requirements.txt by aryamanarora in https://github.com/stanfordnlp/pyvene/pull/140
* [Minor] version bump by frankaging in https://github.com/stanfordnlp/pyvene/pull/141


**Full Changelog**: https://github.com/stanfordnlp/pyvene/compare/v0.0.8...v0.0.9

What's Changed
* [Minor] Add in trainable intervention based on binary mask intervention by frankaging in https://github.com/stanfordnlp/pyvene/pull/102
* [P1] Gradent interventions tests by ZhengPeterWang in https://github.com/stanfordnlp/pyvene/pull/103
* [Minor] Adding retry to gradient test cases to avoid failure by frankaging in https://github.com/stanfordnlp/pyvene/pull/104
* [Minor] Adding support for any two-input lambda interventions; ResNet tutorials (no config) by frankaging in https://github.com/stanfordnlp/pyvene/pull/105
* [Minor] Enable gradient for base inputs by frankaging in https://github.com/stanfordnlp/pyvene/pull/107
* [Minor] Adding an exploratory tutorial on voting in LLaMA by frankaging in https://github.com/stanfordnlp/pyvene/pull/108
* [P1] Added BLIP-ITM model definitions by KhoomeiK in https://github.com/stanfordnlp/pyvene/pull/106
* [Minor] Fix typo in the voting tutorial; fix a bug in generation by frankaging in https://github.com/stanfordnlp/pyvene/pull/109
* [Minor] Adding in subspace support for lambda by frankaging in https://github.com/stanfordnlp/pyvene/pull/113
* Merge main into peterwz by ZhengPeterWang in https://github.com/stanfordnlp/pyvene/pull/115
* [P1] Update transformers version by ZhengPeterWang in https://github.com/stanfordnlp/pyvene/pull/116
* Add GPT2 for sequence classification by atticusg in https://github.com/stanfordnlp/pyvene/pull/117
* [P1] Disable base output by default in fwd() and gen() by frankaging in https://github.com/stanfordnlp/pyvene/pull/118
* [P2] IOI replication notebooks by aryamanarora in https://github.com/stanfordnlp/pyvene/pull/119
* [P0] Rename train/evaluate methods so train/eval can set model state by aryamanarora in https://github.com/stanfordnlp/pyvene/pull/120
* [P1] Add `IntervenableModel.named_parameters()` by aryamanarora in https://github.com/stanfordnlp/pyvene/pull/122
* [P0] Fix unseen model type support by frankaging in https://github.com/stanfordnlp/pyvene/pull/123
* [Minor] Support zero_grad as a module by frankaging in https://github.com/stanfordnlp/pyvene/pull/124
* [Minor] Allow other field passing in generate besides input_ids by frankaging in https://github.com/stanfordnlp/pyvene/pull/125
* [Minor] Loading interventions as non-static method by frankaging in https://github.com/stanfordnlp/pyvene/pull/126
* [Minor] Expose more APIs for loading and saving by frankaging in https://github.com/stanfordnlp/pyvene/pull/127
* [Minor] Update README.md by frankaging in https://github.com/stanfordnlp/pyvene/pull/128
* [Minor] Allow sharing interventions across multiple positions by frankaging in https://github.com/stanfordnlp/pyvene/pull/129
* [Minor] Fix the pyvene101 with correct examples by frankaging in https://github.com/stanfordnlp/pyvene/pull/130
* Test Cases for Causal Model, MQNLI Intro Notebook by amirzur2023 in https://github.com/stanfordnlp/pyvene/pull/131
* [Minor] Update README.md with the correct citation link by frankaging in https://github.com/stanfordnlp/pyvene/pull/132
* [Minor] Update CONTRIBUTING.md by eltociear in https://github.com/stanfordnlp/pyvene/pull/133
* [Minor] Support MistralModel and MistralForCausalLM by jiudingsun01 in https://github.com/stanfordnlp/pyvene/pull/135
* [Minor] Accepting `labels` field for loss calculation by frankaging in https://github.com/stanfordnlp/pyvene/pull/136

New Contributors
* KhoomeiK made their first contribution in https://github.com/stanfordnlp/pyvene/pull/106
* amirzur2023 made their first contribution in https://github.com/stanfordnlp/pyvene/pull/131
* eltociear made their first contribution in https://github.com/stanfordnlp/pyvene/pull/133

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

**Descriptions:**
- Remove redundant keywords `Intervenable` for singleton classes or types everywhere.
- API supports a wide range of dynamic casting, and dynamic broadcasting.
- Providing additional code examples on intervention sharing and complex causal intervention schemes.
- Update basic 101 tutorials with simple onboarding examples.

What's Changed
* Make self.embed_dim not None. by ZhengPeterWang in https://github.com/stanfordnlp/pyvene/pull/49
* [Minor] allow dynamic boundary init for boundless das by frankaging in https://github.com/stanfordnlp/pyvene/pull/50
* [Minor] Minor change to test with num of label by frankaging in https://github.com/stanfordnlp/pyvene/pull/55
* [Minor] add simple location broadcast for easy interface (52) by frankaging in https://github.com/stanfordnlp/pyvene/pull/56
* [Minor] update test name by frankaging in https://github.com/stanfordnlp/pyvene/pull/58
* [P1] Adding in constant source intervention support with new tests by frankaging in https://github.com/stanfordnlp/pyvene/pull/59
* [Minor] Add in full causal tracing fig 1 reproduced results by frankaging in https://github.com/stanfordnlp/pyvene/pull/60
* [Minor] Update to full reproduce result fig1 the ROME paper by frankaging in https://github.com/stanfordnlp/pyvene/pull/61
* [Minor] incidental changes to the tutorials for updated results by frankaging in https://github.com/stanfordnlp/pyvene/pull/65
* Zen/causaltracingfull by frankaging in https://github.com/stanfordnlp/pyvene/pull/66
* [Minor] update broadcast in generation by frankaging in https://github.com/stanfordnlp/pyvene/pull/69
* Model generation API simplified and cleanup tech debt on redundant variables by frankaging in https://github.com/stanfordnlp/pyvene/pull/70
* [Bug Fix] Topological order scoring is not accurate by frankaging in https://github.com/stanfordnlp/pyvene/pull/75
* [Major] Update API namings and parameters by frankaging in https://github.com/stanfordnlp/pyvene/pull/78
* [Minor] Update a few doc links by frankaging in https://github.com/stanfordnlp/pyvene/pull/79
* [Minor] Add Viz by frankaging in https://github.com/stanfordnlp/pyvene/pull/80
* gather_neurons() unit tests by ZhengPeterWang in https://github.com/stanfordnlp/pyvene/pull/81
* Add preliminary scatter() function tests by ZhengPeterWang in https://github.com/stanfordnlp/pyvene/pull/82
* Add an extra test on scatter_neurons() testing case with no head. by ZhengPeterWang in https://github.com/stanfordnlp/pyvene/pull/84
* [Minor] Support backpack and replicate by frankaging in https://github.com/stanfordnlp/pyvene/pull/85
* [Bug fix] fix backpack init by frankaging in https://github.com/stanfordnlp/pyvene/pull/87
* More scatter_neurons() tests by ZhengPeterWang in https://github.com/stanfordnlp/pyvene/pull/88
* [Minor] fix requirements.txt to have a more stable Colab experience (86) by frankaging in https://github.com/stanfordnlp/pyvene/pull/89
* Update datagenerators to support tokenizing for LMs by atticusg in https://github.com/stanfordnlp/pyvene/pull/91
* [Major] Update with string access and code refactory (83) by frankaging in https://github.com/stanfordnlp/pyvene/pull/93
* [Minor] adding PR and BUG template by frankaging in https://github.com/stanfordnlp/pyvene/pull/94
* Model utils tests for GPT-2 by ZhengPeterWang in https://github.com/stanfordnlp/pyvene/pull/92
* [Minor] Support ITI Paper Results (68) by frankaging in https://github.com/stanfordnlp/pyvene/pull/95
* [P1] Adaptive changes with pyvene 101 colab by ZhengPeterWang in https://github.com/stanfordnlp/pyvene/pull/96
* [Minor] Fix gradient backprop trainables with upstream interventions by frankaging in https://github.com/stanfordnlp/pyvene/pull/97
* [P0] remove autograd debugging by aryamanarora in https://github.com/stanfordnlp/pyvene/pull/98
* [P2] Update probing tutorial by aryamanarora in https://github.com/stanfordnlp/pyvene/pull/99
* [P1] Add intervention util unit tests by ZhengPeterWang in https://github.com/stanfordnlp/pyvene/pull/100
* [Minor] Bump up pip version by frankaging in https://github.com/stanfordnlp/pyvene/pull/101


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