llmstep project
This model is a Pythia-410m-deduped language model fine-tuned on LeanDojo Benchmark 4.
The model is fine-tuned on sequences of the form:
[GOAL]tactic-state[PROOFSTEP]next-tactic<|endoftext|>
- Downloads last month
- 7
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support