| Name |
Last commit
|
Last update |
|---|---|---|
| .. | ||
| data_preprocess | ||
| generation | ||
| ppo_trainer | ||
| ray | ||
| sft/gsm8k |
* [deps] fix: make wandb optional dependency * allow ppo scripts to take additional args * fix lint
| Name |
Last commit
|
Last update |
|---|---|---|
| .. | ||
| data_preprocess | Loading commit data... | |
| generation | Loading commit data... | |
| ppo_trainer | Loading commit data... | |
| ray | Loading commit data... | |
| sft/gsm8k | Loading commit data... |