1e-5_test_scripts-step-50 / README.md

verl GRPO trained model at step 50

e79d8eb verified 4 days ago

155 Bytes

metadata

base_model: thejaminator/checkpoints_multiple_datasets_layer_1_decoder-fixed
library_name: peft
tags:
  - lora
  - peft
pipeline_tag: text-generation