RichardErkhov/TIGER-Lab_-_MAmmoTH2-8x7B-Plus-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MAmmoTH2-8x7B-Plus - GGUF

• Model creator: https://huggingface.co/TIGER-Lab/
• Original model: https://huggingface.co/TIGER-Lab/MAmmoTH2-8x7B-Plus/

Name	Quant method	Size
MAmmoTH2-8x7B-Plus.Q2_K.gguf	Q2_K	16.12GB
MAmmoTH2-8x7B-Plus.IQ3_XS.gguf	IQ3_XS	18.02GB
MAmmoTH2-8x7B-Plus.IQ3_S.gguf	IQ3_S	19.03GB
MAmmoTH2-8x7B-Plus.Q3_K_S.gguf	Q3_K_S	19.03GB
MAmmoTH2-8x7B-Plus.IQ3_M.gguf	IQ3_M	19.96GB
MAmmoTH2-8x7B-Plus.Q3_K.gguf	Q3_K	21.0GB
MAmmoTH2-8x7B-Plus.Q3_K_M.gguf	Q3_K_M	21.0GB
MAmmoTH2-8x7B-Plus.Q3_K_L.gguf	Q3_K_L	22.51GB
MAmmoTH2-8x7B-Plus.IQ4_XS.gguf	IQ4_XS	23.63GB
MAmmoTH2-8x7B-Plus.Q4_0.gguf	Q4_0	24.63GB
MAmmoTH2-8x7B-Plus.IQ4_NL.gguf	IQ4_NL	24.91GB
MAmmoTH2-8x7B-Plus.Q4_K_S.gguf	Q4_K_S	24.91GB
MAmmoTH2-8x7B-Plus.Q4_K.gguf	Q4_K	26.49GB
MAmmoTH2-8x7B-Plus.Q4_K_M.gguf	Q4_K_M	26.49GB
MAmmoTH2-8x7B-Plus.Q4_1.gguf	Q4_1	27.32GB
MAmmoTH2-8x7B-Plus.Q5_0.gguf	Q5_0	30.02GB
MAmmoTH2-8x7B-Plus.Q5_K_S.gguf	Q5_K_S	30.02GB
MAmmoTH2-8x7B-Plus.Q5_K.gguf	Q5_K	30.95GB
MAmmoTH2-8x7B-Plus.Q5_K_M.gguf	Q5_K_M	30.95GB
MAmmoTH2-8x7B-Plus.Q5_1.gguf	Q5_1	32.71GB
MAmmoTH2-8x7B-Plus.Q6_K.gguf	Q6_K	35.74GB
MAmmoTH2-8x7B-Plus.Q8_0.gguf	Q8_0	46.22GB

Original model description:

license: mit language: - en datasets: - TIGER-Lab/WebInstructSub metrics: - accuracy library_name: transformers

🦣 MAmmoTH2: Scaling Instructions from the Web

Project Page: https://tiger-ai-lab.github.io/MAmmoTH2/

Paper: https://arxiv.org/pdf/2405.03548

Code: https://github.com/TIGER-AI-Lab/MAmmoTH2

Introduction

Introducing 🦣 MAmmoTH2, a game-changer in improving the reasoning abilities of large language models (LLMs) through innovative instruction tuning. By efficiently harvesting 10 million instruction-response pairs from the pre-training web corpus, we've developed MAmmoTH2 models that significantly boost performance on reasoning benchmarks. For instance, MAmmoTH2-7B (Mistral) sees its performance soar from 11% to 36.7% on MATH and from 36% to 68.4% on GSM8K, all without training on any domain-specific data. Further training on public instruction tuning datasets yields MAmmoTH2-Plus, setting new standards in reasoning and chatbot benchmarks. Our work presents a cost-effective approach to acquiring large-scale, high-quality instruction data, offering a fresh perspective on enhancing LLM reasoning abilities.

	Base Model	MAmmoTH2	MAmmoTH2-Plus
7B	Mistral	🦣 MAmmoTH2-7B	🦣 MAmmoTH2-7B-Plus
8B	Llama-3	🦣 MAmmoTH2-8B	🦣 MAmmoTH2-8B-Plus
8x7B	Mixtral	🦣 MAmmoTH2-8x7B	🦣 MAmmoTH2-8x7B-Plus

Training Data

Please refer to https://huggingface.co/datasets/TIGER-Lab/WebInstructSub for more details.

Training Procedure

The models are fine-tuned with the WEBINSTRUCT dataset using the original Llama-3, Mistral and Mistal models as base models. The training procedure varies for different models based on their sizes. Check out our paper for more details.

Evaluation

The models are evaluated using open-ended and multiple-choice math problems from several datasets. Here are the results:

Model	TheoremQA	MATH	GSM8K	GPQA	MMLU-ST	BBH	ARC-C	Avg
MAmmoTH2-7B (Updated)	29.0	36.7	68.4	32.4	62.4	58.6	81.7	52.7
MAmmoTH2-8B (Updated)	30.3	35.8	70.4	35.2	64.2	62.1	82.2	54.3
MAmmoTH2-8x7B	32.2	39.0	75.4	36.8	67.4	71.1	87.5	58.9
MAmmoTH2-7B-Plus (Updated)	31.2	46.0	84.6	33.8	63.8	63.3	84.4	58.1
MAmmoTH2-8B-Plus (Updated)	31.5	43.0	85.2	35.8	66.7	69.7	84.3	59.4
MAmmoTH2-8x7B-Plus	34.1	47.0	86.4	37.8	72.4	74.1	88.4	62.9

To reproduce our results, please refer to https://github.com/TIGER-AI-Lab/MAmmoTH2/tree/main/math_eval.

Chat Format

The template used to build a prompt for the Instruct model is defined as follows:

<s> [INST] Instruction [/INST] Model answer</s> [INST] Follow-up instruction [/INST]

Note that <s> and </s> are special tokens for beginning of string (BOS) and end of string (EOS) while [INST] and [/INST] are regular strings.

But we also found that the model is not very sensitive to the chat template.

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 more advanced use: https://github.com/TIGER-AI-Lab/MAmmoTH2

Limitations

We've tried our best to build math generalist models. However, we acknowledge that the models' performance may vary based on the complexity and specifics of the math problem. Still not all mathematical fields can be covered comprehensively.

Citation

If you use the models, data, or code from this project, please cite the original paper:

@article{yue2024mammoth2,
  title={MAmmoTH2: Scaling Instructions from the Web},
  author={Yue, Xiang and Zheng, Tuney and Zhang, Ge and Chen, Wenhu},
  journal={arXiv preprint arXiv:2405.03548},
  year={2024}
}