RichardErkhov/gair-prox_-_math-doc-refining-lm-awq

Quantization made by Richard Erkhov.

Github

Discord

Request more models

math-doc-refining-lm - AWQ

• Model creator: https://huggingface.co/gair-prox/
• Original model: https://huggingface.co/gair-prox/math-doc-refining-lm/

Original model description:

license: apache-2.0 datasets: - gair-prox/RedPajama-pro language: - en base_model: - gair-prox/RedPJ-ProX-0.7B pipeline_tag: text-generation library_name: transformers tags: - llama - code

Math-doc-refining-lm

ArXiv | Code

Math-doc-refining-lm is an adapted 0.7B-ProX model, fine-tuned for doc level refining via program generation, and can be applied over math pre-training corpus such as open-web-math.

Citation

@article{zhou2024programming,
  title={Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale},
  author={Zhou, Fan and Wang, Zengzhi and Liu, Qian and Li, Junlong and Liu, Pengfei},
  journal={arXiv preprint arXiv:2409.17115},
  year={2024}
}