open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-19 12:58:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

update config to latest veRL version

Browse source
This commit is contained in:
Andreas Koepf 2025-02-17 18:43:51 +00:00
parent 79c5e53ef0
commit 2ae21c6548
2 changed files with 23 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

19
examples/veRL/README.md
View file

@ -1,19 +1,32 @@
### env setup
```
conda create --name verl python=3.12 -y
conda create --name verl python=3.11 -y
conda activate verl
pip install flash-attn --no-build-isolation
pip install vllm==0.7.0 ray wandb
pip install ray wandb
# pip3 install vllm==0.7.0
pip3 install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
```
Regarding vllm>0.7 see: [docs](https://verl.readthedocs.io/en/latest/README_vllm0.7.html)
### clone and install veRL
tested with verl HEAD a65c9157bc0b85b64cd753de19f94e80a11bd871
tested with verl HEAD 0dfcb7f99e299940e1792a386df13c7591df351a
```
git clone https://github.com/volcengine/verl.git
cd verl
pip install -e .
```
Optionally log in to huggingface hub and wandb with your keys:
```
huggingface-cli login
wandb login
```