Programming by example induction model after RL training for 6K steps. This has been trained for accuracay and shortness (length penalty 1e-3).
Started from SFT checkpoint abhishekraok/induction-basicfns-opt125m-longsft.
See https://github.com/abhishekraok/wandering-light for details.
- Downloads last month
- 10
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for abhishekraok/induction-basicfns-opt125m-sft434k-rl-6k-with-lp
Base model
facebook/opt-125m