zswzswzsw
/

verl_subquestion

Model card Files Files and versions

verl_subquestion / examples /tuning /7b

5.24 kB

1 contributor

History: 1 commit

zswzswzsw's picture

Upload folder using huggingface_hub

66407c5 verified about 2 months ago

qwen2-7b_grpo-lora_1_h100_fsdp_vllm.sh

3.24 kB

Upload folder using huggingface_hub about 2 months ago
qwen2-7b_grpo_2_h800_fsdp_vllm.sh

2 kB

Upload folder using huggingface_hub about 2 months ago