open-r1/scripts
lewtun 8000dd2384
[WIP] RL goes brrr (#533)
* Fix vLLM recipes

* Add vllm server to Slurm

* Add overlap across srun

* Fix NUM_NODES

* Refactor TP to script

* fix train script to work withnew  GRPO

* lewis nits

* bump trl, transformers

---------

Co-authored-by: edbeeching <edbeeching@gmail.com>
2025-03-24 15:15:02 +01:00
..
decontaminate.py Enable decontamination on dataset configs (#460) 2025-03-04 09:22:01 +01:00
generate_reasoning.py Fix uuid in the data generator (#284) 2025-02-11 14:08:46 +01:00
get_tensor_parallel_size.py [WIP] RL goes brrr (#533) 2025-03-24 15:15:02 +01:00
run_benchmarks.py use ruff (#137) 2025-01-31 13:36:08 +01:00
upload_details.py move details script and fix wandb logging (#314) 2025-02-13 11:13:00 +01:00