Holarissun
/

RM-HH-GPT2-4w_helpful_gpt3_loraR64_40000_gpt2-large_shuffleTrue_extractchosenFalse

Generated from Trainer

Model card Files Files and versions Community

RM-HH-GPT2-4w_helpful_gpt3_loraR64_40000_gpt2-large_shuffleTrue_extractchosenFalse / merges.txt

Commit History

End of training

2546cf1
verified

Holarissun commited on Apr 25