baukit_orth_act_steering.ipynb

pyproject.toml

[tool.poetry]
name = "strer_llms"
version = "0.1.0"
description = ""
authors = [""]
license = "MIT"
readme = "README.md"

[tool.poetry.dependencies]
python = ">=3.10,<3.13"
torch = {version = "^2.2.2+cu121", source = "pytorch"}
simple-parsing = "^0.1.4"
tqdm = "^4.66.1"
numpy = "^1.26.1"
pandas = "^2.1.1"
lightning = "^2.1.0"
matplotlib = "^3.8.0"
loguru = "^0.7.2"
einops = "^0.7.0"
scikit-learn = "^1.3.1"
pytorch-optimizer = "^2.12.0"
torchinfo = "^1.8.0"
transformers-stream-generator = "^0.0.5"
tiktoken = "^0.6.0"
baukit = {git = "https://github.com/davidbau/baukit"}
jaxtyping = "^0.2.28"
colorama = "^0.4.6"
pytest = "^8.2.0"
outlines = "^0.0.41"

[[tool.poetry.source]]
name = "pytorch"
url = "https://download.pytorch.org/whl/cu121"
priority = "explicit"


[tool.poetry.group.dev.dependencies]
ipykernel = "^6.25.2"
ruff = "^0.1.3"
pylama = "^8.4.1"

[build-system]
requires = ["poetry-core"]
build-backend = "poetry.core.masonry.api"

idk, somethings not compatible, but it's hard to know what's changed for you

it might be worth trying this newer lib https://github.com/FailSpy/abliterator, failspy has some great code and has gone further than me at this point

I solved the problem by run model in single card. thank you for sharing the new library haha.