mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-19 12:58:07 +00:00
9 lines
205 B
Bash
Executable file
9 lines
205 B
Bash
Executable file
#!/bin/bash
|
|
|
|
export N_GPUS=4
|
|
export BASE_MODEL=meta-llama/Llama-3.2-1B-Instruct
|
|
export ROLLOUT_TP_SIZE=2
|
|
export EXPERIMENT_NAME=chain_sum_llama
|
|
export VLLM_ATTENTION_BACKEND=XFORMERS
|
|
|
|
bash ./train_grpo.sh
|