Files
alphamath_round2/README.md

9 lines
284 B
Markdown
Raw Permalink Normal View History

---
license: mit
base_model:
- deepseek-ai/deepseek-math-7b-base
---
Replication of method from [AlphaMath Almost Zero: Process Supervision without Process](https://arxiv.org/abs/2405.03553).
See https://github.com/MARIO-Math-Reasoning/Super_MARIO/tree/main for inference procedure.