vwxyzjn
/

ppo_zephyr_vllm_1e-6_kl_0.15

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

Metrics Training metrics Community

ppo_zephyr_vllm_1e-6_kl_0.15 / runs

1.62 MB

1 contributor

History: 1 commit

vwxyzjn's picture

End of training

79f097e verified over 1 year ago