quyanh
/

pythia-2.8b-dpo

Generated from Trainer

Model card Files Files and versions

pythia-2.8b-dpo / tokenizer.json

quyanh's picture

Tokenizer - DPO LoRA checkpoint - step 100 (eval_loss: 0.6984)

13dc6b8 verified 10 months ago

history contribute delete

3.56 MB

File too large to display, you can check the raw version instead.