absl-py==2.1.0
accelerate==0.34.2
aiohappyeyeballs==2.4.0
aiohttp==3.10.5
aiosignal==1.3.1
aniso8601==9.0.1
annotated-types==0.7.0
antlr4-python3-runtime==4.9.3
anyio==4.4.0
argon2-cffi==23.1.0
argon2-cffi-bindings==21.2.0
arrow==1.3.0
asciitree==0.3.3
asttokens==2.4.1
astunparse==1.6.3
async-lru==2.0.4
async-timeout==4.0.3
attrs==24.2.0
autoawq==0.2.6
autoawq_kernels @ file:///mnt/datadisk/raglab/sync-data-generation/AutoAWQ_kernels/precompiled_dist/autoawq_kernels-0.0.6%2Bcu121-cp310-cp310-linux_x86_64.whl#sha256=649675f67fbe6a1f11cf0b298480c4220e3db8e8b55d2a9fad551602c71cc926
awscli==1.34.19
babel==2.16.0
beautifulsoup4==4.12.3
bitsandbytes==0.43.3
bleach==6.1.0
blinker==1.8.2
blis==0.7.11
bokeh==3.5.2
bonito @ file:///mnt/datadisk/raglab/sync-data-generation/bonito
boto3==1.35.19
botocore==1.35.19
braceexpand==0.1.7
Brotli==1.1.0
cachetools==5.5.0
catalogue==2.0.10
certifi==2024.8.30
cffi==1.17.1
charset-normalizer==3.3.2
click==8.1.7
cloudpathlib==0.19.0
cloudpickle==3.0.0
colorama==0.4.6
comm==0.2.2
comment-parser==1.2.4
confection==0.1.5
contourpy==1.3.0
crossfit @ git+https://github.com/rapidsai/crossfit.git@69de99b9e13eb1fb5c51ed8eee5cc0607e664c92
cuda-python==12.6.0
cudf-cu12==24.8.2
cuml-cu12==24.8.0
cupy-cuda12x==13.3.0
cycler==0.12.1
cymem==2.0.8
Cython==3.0.11
dask==2024.7.1
dask-cuda==24.8.2
dask-cudf-cu12==24.8.2
dask-expr==1.1.9
dask-mpi==2022.4.0
data-gemma==0.0.1
dataclasses-json==0.6.7
datasets==3.0.0
debugpy==1.8.5
decorator==5.1.1
defusedxml==0.7.1
Deprecated==1.2.14
dill==0.3.8
dirtyjson==1.0.8
diskcache==5.6.3
distributed==2024.7.1
distributed-ucxx-cu12==0.39.1
distro==1.9.0
docker-pycreds==0.4.0
docutils==0.16
einops==0.8.0
exceptiongroup==1.2.2
executing==2.1.0
faiss-cpu==1.8.0.post1
fastapi==0.114.2
fasteners==0.19
fastjsonschema==2.20.0
fastrlock==0.8.2
fasttext==0.9.2
FastWARC==0.14.9
filelock==3.16.0
flash-attn==2.5.6
Flask==3.0.3
Flask-RESTful==0.3.10
fonttools==4.53.1
fqdn==1.5.1
frozenlist==1.4.1
fsspec==2024.6.1
ftfy==6.1.1
future==1.0.0
gdown==5.2.0
gguf==0.9.1
gitdb==4.0.11
GitPython==3.1.43
greenlet==3.1.0
grpcio==1.66.1
h11==0.14.0
h5py==3.11.0
hf_transfer==0.1.8
httpcore==1.0.5
httptools==0.6.1
httpx==0.27.2
huggingface-hub==0.24.7
hydra-core==1.3.2
idna==3.10
ijson==3.3.0
importlib_metadata==8.5.0
in-place==0.5.0
inflect==7.4.0
interegular==0.3.3
ipykernel==6.29.5
ipython==8.27.0
ipywidgets==8.1.3
isoduration==20.11.0
itsdangerous==2.2.0
jedi==0.19.1
jieba==0.42.1
Jinja2==3.1.4
jiter==0.5.0
jmespath==1.0.1
joblib==1.4.2
json5==0.9.25
jsonpointer==3.0.0
jsonschema==4.23.0
jsonschema-specifications==2023.12.1
jupyter-events==0.10.0
jupyter-lsp==2.2.5
jupyter_client==8.6.2
jupyter_core==5.7.2
jupyter_server==2.14.2
jupyter_server_terminals==0.5.3
jupyterlab==4.2.5
jupyterlab_pygments==0.3.0
jupyterlab_server==2.27.3
jupyterlab_widgets==3.0.13
jusText==3.0.1
kiwisolver==1.4.7
langcodes==3.4.0
language_data==1.2.0
lark==1.2.2
libucx-cu12==1.15.0.post1
lightning-utilities==0.11.7
llama-cloud==0.0.6
llama-index-core==0.10.68.post1
llama-index-embeddings-nvidia==0.1.4
llama-index-llms-nvidia==0.1.3
llama-index-llms-openai==0.1.31
llama-index-llms-openai-like==0.1.3
llama-index-postprocessor-nvidia-rerank==0.1.2
llama-index-readers-file==0.1.25
llvmlite==0.43.0
lm-format-enforcer==0.10.6
locket==1.0.0
lxml==5.3.0
lxml_html_clean==0.2.2
lz4==4.3.3
marisa-trie==1.2.0
Markdown==3.7
markdown-it-py==3.0.0
markdown2==2.5.0
MarkupSafe==2.1.5
marshmallow==3.22.0
matplotlib==3.9.2
matplotlib-inline==0.1.7
mdurl==0.1.2
megatron_core==0.5.0
mistral_common==1.4.0
mistune==3.0.2
more-itertools==10.5.0
mpmath==1.3.0
msgpack==1.1.0
msgspec==0.18.6
multidict==6.1.0
multiprocess==0.70.16
murmurhash==1.0.10
mwparserfromhell==0.6.5
mypy-extensions==1.0.0
nbclient==0.10.0
nbconvert==7.16.4
nbformat==5.10.4
nemo_curator @ file:///mnt/datadisk/raglab/NeMo-Curator
nemo_toolkit==1.23.0
nest-asyncio==1.6.0
networkx==3.3
ninja==1.11.1.1
nltk==3.9.1
notebook_shim==0.2.4
numba==0.60.0
numcodecs==0.13.0
numpy==1.26.4
nvidia-cublas-cu12==12.1.3.1
nvidia-cuda-cupti-cu12==12.1.105
nvidia-cuda-nvrtc-cu12==12.1.105
nvidia-cuda-runtime-cu12==12.1.105
nvidia-cudnn-cu12==9.1.0.70
nvidia-cufft-cu12==11.0.2.54
nvidia-curand-cu12==10.3.2.106
nvidia-cusolver-cu12==11.4.5.107
nvidia-cusparse-cu12==12.1.0.106
nvidia-ml-py==12.560.30
nvidia-nccl-cu12==2.20.5
nvidia-nvjitlink-cu12==12.6.68
nvidia-nvtx-cu12==12.1.105
nvtx==0.2.10
omegaconf==2.3.0
onnx==1.16.2
openai==1.45.1
OpenCC==1.1.6
outlines==0.0.46
overrides==7.7.0
packaging==24.1
pandas==2.2.2
pandocfilters==1.5.1
pangu==4.0.6.1
parso==0.8.4
partd==1.4.2
partial-json-parser==0.2.1.1.post4
peft==0.12.0
pexpect==4.9.0
phonenumbers==8.13.45
pillow==10.4.0
platformdirs==4.3.3
portalocker==2.10.1
preshed==3.0.9
presidio-analyzer==2.2.351
presidio-anonymizer==2.2.351
probableparsing==0.0.1
prometheus-fastapi-instrumentator==7.0.0
prometheus_client==0.20.0
prompt_toolkit==3.0.47
protobuf==3.20.3
psutil==6.0.0
ptyprocess==0.7.0
pure_eval==0.2.3
py-cpuinfo==9.0.0
pyairports==2.1.1
pyarrow==16.1.0
pyarrow-hotfix==0.6
pyasn1==0.6.1
pybind11==2.13.6
pycld2==0.41
pycountry==24.6.1
pycparser==2.22
pycryptodome==3.20.0
pydantic==2.9.1
pydantic_core==2.23.3
Pygments==2.18.0
pylibraft-cu12==24.8.1
pynvjitlink-cu12==0.3.0
pyparsing==3.1.4
pypdf==4.3.1
PySocks==1.7.1
python-crfsuite==0.9.10
python-dateutil==2.9.0.post0
python-dotenv==1.0.1
python-json-logger==2.0.7
python-magic==0.4.24
pytorch-lightning==2.0.7
pytz==2024.2
PyYAML==6.0.2
pyzmq==26.2.0
raft-dask-cu12==24.8.1
rapidfuzz==3.9.7
rapids-dask-dependency==24.8.0
ray==2.35.0
referencing==0.35.1
regex==2024.9.11
requests==2.32.3
requests-file==2.1.0
Resiliparse==0.14.9
rfc3339-validator==0.1.4
rfc3986-validator==0.1.1
rich==13.8.1
rmm-cu12==24.8.2
rouge-score==0.1.2
rpds-py==0.20.0
rsa==4.7.2
ruamel.yaml==0.18.6
ruamel.yaml.clib==0.2.8
s3transfer==0.10.2
sacrebleu==2.4.3
sacremoses==0.1.1
safetensors==0.4.5
scikit-learn==1.1.3
scipy==1.14.1
Send2Trash==1.8.3
sentence-transformers==3.1.0
sentencepiece==0.2.0
sentry-sdk==2.14.0
setproctitle==1.3.3
shellingham==1.5.4
six==1.16.0
smart-open==7.0.4
smmap==5.0.1
sniffio==1.3.1
sortedcontainers==2.4.0
soupsieve==2.6
spacy==3.7.6
spacy-legacy==3.0.12
spacy-loggers==1.0.5
SQLAlchemy==2.0.34
srsly==2.4.8
stack-data==0.6.3
starlette==0.38.5
striprtf==0.0.26
sympy==1.13.2
tabulate==0.9.0
tblib==3.0.0
tenacity==8.5.0
tensorboard==2.17.1
tensorboard-data-server==0.7.2
tensorflow-metadata==1.15.0
tensorstore==0.1.45
terminado==0.18.1
text-unidecode==1.3
thinc==8.2.5
threadpoolctl==3.5.0
tiktoken==0.7.0
tinycss2==1.3.0
tldextract==5.1.2
tokenizers==0.19.1
tomli==2.0.1
toolz==0.12.1
torch==2.4.0+cu121
torchaudio==2.4.0+cu121
torchmetrics==1.4.2
torchvision==0.19.0
tornado==6.4.1
tqdm==4.66.5
traitlets==5.14.3
transformers==4.44.2
treelite==4.3.0
triton==3.0.0
typeguard==4.3.0
typer==0.12.5
types-python-dateutil==2.9.0.20240906
typing-inspect==0.9.0
typing-utils==0.1.0
typing_extensions==4.12.2
tzdata==2024.1
ucx-py-cu12==0.39.2
ucxx-cu12==0.39.1
unidic-lite==1.0.8
uri-template==1.3.0
urllib3==2.2.3
usaddress==0.5.10
uvicorn==0.30.6
uvloop==0.20.0
vllm==0.6.1.post2
vllm-flash-attn==2.6.1
wandb==0.18.0
warcio==1.7.4
wasabi==1.1.3
watchfiles==0.24.0
wcwidth==0.2.13
weasel==0.4.1
webcolors==24.8.0
webdataset==0.1.62
webencodings==0.5.1
websocket-client==1.8.0
websockets==13.0.1
Werkzeug==3.0.4
wget==3.2
widgetsnbextension==4.0.13
wrapt==1.16.0
xformers==0.0.27.post2
xxhash==3.5.0
xyzservices==2024.9.0
yarl==1.11.1
youtokentome==1.0.6
zarr==2.18.3
zict==3.0.0
zipp==3.20.2
zstandard==0.18.0