Holarissun
/

dpo_tldrtldr_gpt4_subset10000_modelgemma2b_maxsteps5000_bz8_lr1e-06

Generated from Trainer

Model card Files Files and versions Community

dpo_tldrtldr_gpt4_subset10000_modelgemma2b_maxsteps5000_bz8_lr1e-06 / tokenizer.json

Commit History

tldr_gpt4_subset10000_modelgemma2b_maxsteps5000_bz8_lr1e-06

4aebec2
verified

Holarissun commited on May 9