Model Card for LLaMATH 7B
This repository contains the delta weights for a LLaMA model fine-tuned for Mathematical Reasoning, Problem-Solving and Instruction Following.
Model Details
Model Description
- Developed by: Alpay Ariyak
- Language(s) (NLP): English
- Finetuned from model: Alpaca 7B
Model Sources [optional]
- Repository: [Coming Soon...]
- Paper [optional]: [Coming Soon...]
- Dataset: Instruction-formatted MATH dataset