GoodStartLabs
/

diplomacy-235b-lora

Text Generation

reinforcement-learning

Model card Files Files and versions

diplomacy-235b-lora

Commit History

Trim model card

0ad00a3
verified

Alex-GSL commited on 9 days ago

Add per-update training metrics (25 steps x 41 metrics)

5f697ec
verified

Alex-GSL commited on 9 days ago

Add model card

3fdd719
verified

Alex-GSL commited on 9 days ago

Diplomacy RL LoRA, final checkpoint (optimizer step 25) from wandb run 7zu4lxjj

9e351d0
verified

Alex-GSL commited on 9 days ago

initial commit

c446f28
verified

Alex-GSL commited on 9 days ago