uclaml / SPIN

The official implementation of Self-Play Fine-Tuning (SPIN)
https://uclaml.github.io/SPIN/
Apache License 2.0
1.05k stars 92 forks source link

Clarify use of revision in SFT checkpoint #17

Closed lewtun closed 9 months ago

lewtun commented 9 months ago

Adds a small note about how people can load the original SFT checkpoint from the handbook. Apologies for changing it!