SVRL
/

verl-scalable-0402_batch768_clipratio0.3_Qwen2.5-7B_scale-reasoning-data-v2-nos-fixmc-fil0-fil8

Model card Files Files and versions Community

verl-scalable-0402_batch768_clipratio0.3_Qwen2.5-7B_scale-reasoning-data-v2-nos-fixmc-fil0-fil8 / global_step_380 /model-00004-of-00007.safetensors

Commit History

Upload global_step_380/model-00004-of-00007.safetensors with huggingface_hub

b2a39d2
verified

SivilTaram commited on Apr 12