RichardErkhov/MathLLMs_-_MathCoder-CL-7B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MathCoder-CL-7B - GGUF

• Model creator: https://huggingface.co/MathLLMs/
• Original model: https://huggingface.co/MathLLMs/MathCoder-CL-7B/

Name	Quant method	Size
MathCoder-CL-7B.Q2_K.gguf	Q2_K	2.36GB
MathCoder-CL-7B.IQ3_XS.gguf	IQ3_XS	2.6GB
MathCoder-CL-7B.IQ3_S.gguf	IQ3_S	2.75GB
MathCoder-CL-7B.Q3_K_S.gguf	Q3_K_S	2.75GB
MathCoder-CL-7B.IQ3_M.gguf	IQ3_M	2.9GB
MathCoder-CL-7B.Q3_K.gguf	Q3_K	3.07GB
MathCoder-CL-7B.Q3_K_M.gguf	Q3_K_M	3.07GB
MathCoder-CL-7B.Q3_K_L.gguf	Q3_K_L	3.35GB
MathCoder-CL-7B.IQ4_XS.gguf	IQ4_XS	3.4GB
MathCoder-CL-7B.Q4_0.gguf	Q4_0	3.56GB
MathCoder-CL-7B.IQ4_NL.gguf	IQ4_NL	3.58GB
MathCoder-CL-7B.Q4_K_S.gguf	Q4_K_S	3.59GB
MathCoder-CL-7B.Q4_K.gguf	Q4_K	3.8GB
MathCoder-CL-7B.Q4_K_M.gguf	Q4_K_M	3.8GB
MathCoder-CL-7B.Q4_1.gguf	Q4_1	3.95GB
MathCoder-CL-7B.Q5_0.gguf	Q5_0	4.33GB
MathCoder-CL-7B.Q5_K_S.gguf	Q5_K_S	4.33GB
MathCoder-CL-7B.Q5_K.gguf	Q5_K	4.45GB
MathCoder-CL-7B.Q5_K_M.gguf	Q5_K_M	4.45GB
MathCoder-CL-7B.Q5_1.gguf	Q5_1	4.72GB
MathCoder-CL-7B.Q6_K.gguf	Q6_K	5.15GB
MathCoder-CL-7B.Q8_0.gguf	Q8_0	6.67GB

Original model description:

license: apache-2.0 language: - en metrics: - accuracy pipeline_tag: text-generation

MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning

Paper: https://arxiv.org/pdf/2310.03731.pdf

Repo: https://github.com/mathllm/MathCoder

Introduction

We introduce MathCoder, a series of open-source large language models (LLMs) specifically tailored for general math problem-solving.

Base Model: Llama-2	Base Model: Code Llama
MathCoder-L-7B	MathCoder-CL-7B
MathCoder-L-13B	MathCoder-CL-34B

Training Data

The models are trained on the MathCodeInstruct Dataset.

Training Procedure

The models are fine-tuned with the MathCodeInstruct dataset using the original Llama-2 and CodeLlama models as base models. Check out our paper and repo for more details.

Evaluation

Usage

You can use the models through Huggingface's Transformers library. Use the pipeline function to create a text-generation pipeline with the model of your choice, then feed in a math problem to get the solution. Check our Github repo for datails.

Citation

Please cite the paper if you use our data, model or code. Please also kindly cite the original dataset papers.

@inproceedings{
wang2024mathcoder,
title={MathCoder: Seamless Code Integration in {LLM}s for Enhanced Mathematical Reasoning},
author={Ke Wang and Houxing Ren and Aojun Zhou and Zimu Lu and Sichun Luo and Weikang Shi and Renrui Zhang and Linqi Song and Mingjie Zhan and Hongsheng Li},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=z8TW0ttBPp}
}

@inproceedings{
zhou2024solving,
title={Solving Challenging Math Word Problems Using {GPT}-4 Code Interpreter with Code-based Self-Verification},
author={Aojun Zhou and Ke Wang and Zimu Lu and Weikang Shi and Sichun Luo and Zipeng Qin and Shaoqing Lu and Anya Jia and Linqi Song and Mingjie Zhan and Hongsheng Li},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=c8McWs4Av0}
}