2

.gitignore

@@ -0,0 +1,179 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+data/
+save_for_eval/
+models/
+
+# LSP config files
+pyrightconfig.json
+
+# End of https://www.toptal.com/developers/gitignore/api/python

a.sh

@@ -0,0 +1,2 @@
+export HF_ENDPOINT=https://hf-mirror.com
+CUDA_VISIBLE_DEVICES=0 python hal_det_llama.py --dataset_name triviaqa --model_name llama2_chat_7B --most_likely 0 --use_rouge 0 --generate_gt 1

b.sh

@@ -0,0 +1,2 @@
+export HF_ENDPOINT=https://hf-mirror.com
+CUDA_VISIBLE_DEVICES=2 python hal_det_llama.py --dataset_name triviaqa --model_name llama2_chat_7B --use_rouge 0 --most_likely 1 --weighted_svd 1 --feat_loc_svd 3

env.yml

@@ -1,4 +1,4 @@
-name: base
+name: haloscope
 channels:
   - conda-forge
   - defaults

hal_det_llama.py

@@ -4,10 +4,11 @@ import torch.nn.functional as F
 import evaluate
 from datasets import load_metric
 from datasets import load_dataset
+import datasets
 from tqdm import tqdm
 import numpy as np
 import pickle
-from utils import get_llama_activations_bau, tokenized_tqa, tokenized_tqa_gen, tokenized_tqa_gen_end_q
+# from utils import get_llama_activations_bau, tokenized_tqa, tokenized_tqa_gen, tokenized_tqa_gen_end_q
 import llama_iti
 import pickle
 import argparse
@@ -49,7 +50,7 @@ def main():
 
     parser = argparse.ArgumentParser()
     parser.add_argument('--model_name', type=str, default='llama2_chat_7B')
-    parser.add_argument('--dataset_name', type=str, default='tqa')
+    parser.add_argument('--dataset_name', type=str, default='triviaqa')
     parser.add_argument('--num_gene', type=int, default=1)
     parser.add_argument('--gene', type=int, default=0)
     parser.add_argument('--generate_gt', type=int, default=0)
@@ -240,8 +241,8 @@ def main():
     elif args.generate_gt:
         from bleurt_pytorch import BleurtConfig, BleurtForSequenceClassification, BleurtTokenizer
 
-        model = BleurtForSequenceClassification.from_pretrained('./models/BLEURT-20').cuda()
-        tokenizer = BleurtTokenizer.from_pretrained('./models/BLEURT-20')
+        model = BleurtForSequenceClassification.from_pretrained('lucadiliello/BLEURT-20').cuda()
+        tokenizer = BleurtTokenizer.from_pretrained('lucadiliello/BLEURT-20')
         model.eval()
 
         rouge = evaluate.load('rouge')