readCtrl_lambda / code /RL_model /verl /verl_train /requirements_sglang.txt
mshahidul
Initial commit of readCtrl code without large models
030876e
# requirements.txt records the full set of dependencies for development
accelerate
codetiming
datasets
dill
flash-attn
hydra-core
numpy<2.0.0
pandas
peft
pyarrow>=19.0.0
pybind11
pylatexenc
ray[default]>=2.10
tensordict>=0.8.0,<=0.10.0,!=0.9.0
torchdata
torchvision
transformers
wandb
sglang[all]==0.5.2
huggingface_hub