TheBloke/MAmmoTH-7B-GGUF

Chat & support: TheBloke's Discord server

Want to contribute? TheBloke's Patreon page

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)

---

MAmmoTH 7B - GGUF

• Model creator: TIGER-Lab
• Original model: MAmmoTH 7B

Description

This repo contains GGUF format model files for TIGER-Lab's MAmmoTH 7B.

About GGUF

GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.

Here is an incomplate list of clients and libraries that are known to support GGUF:

• llama.cpp. The source project for GGUF. Offers a CLI and a server option.
• text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
• KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
• LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
• LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
• Faraday.dev, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
• ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
• llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
• candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.

Repositories available

• AWQ model(s) for GPU inference.
• GPTQ models for GPU inference, with multiple quantisation parameter options.
• 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference
• TIGER-Lab's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

Licensing

The creator of the source model has listed its license as mit, and this quantization has therefore used that same license.

As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.

In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: TIGER-Lab's MAmmoTH 7B.

Compatibility

These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit d0cee0d

They are also compatible with many third party UIs and libraries - please see the list at the top of this README.

Explanation of quantisation methods

Click to see details

The new methods available are:

• GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
• GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
• GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
• GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
• GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw

Refer to the Provided Files table below to see what files use which methods, and how.

Provided files

Name	Quant method	Bits	Size	Max RAM required	Use case
mammoth-7b.Q2_K.gguf	Q2_K	2	2.83 GB	5.33 GB	smallest, significant quality loss - not recommended for most purposes
mammoth-7b.Q3_K_S.gguf	Q3_K_S	3	2.95 GB	5.45 GB	very small, high quality loss
mammoth-7b.Q3_K_M.gguf	Q3_K_M	3	3.30 GB	5.80 GB	very small, high quality loss
mammoth-7b.Q3_K_L.gguf	Q3_K_L	3	3.60 GB	6.10 GB	small, substantial quality loss
mammoth-7b.Q4_0.gguf	Q4_0	4	3.83 GB	6.33 GB	legacy; small, very high quality loss - prefer using Q3_K_M
mammoth-7b.Q4_K_S.gguf	Q4_K_S	4	3.86 GB	6.36 GB	small, greater quality loss
mammoth-7b.Q4_K_M.gguf	Q4_K_M	4	4.08 GB	6.58 GB	medium, balanced quality - recommended
mammoth-7b.Q5_0.gguf	Q5_0	5	4.65 GB	7.15 GB	legacy; medium, balanced quality - prefer using Q4_K_M
mammoth-7b.Q5_K_S.gguf	Q5_K_S	5	4.65 GB	7.15 GB	large, low quality loss - recommended
mammoth-7b.Q5_K_M.gguf	Q5_K_M	5	4.78 GB	7.28 GB	large, very low quality loss - recommended
mammoth-7b.Q6_K.gguf	Q6_K	6	5.53 GB	8.03 GB	very large, extremely low quality loss
mammoth-7b.Q8_0.gguf	Q8_0	8	7.16 GB	9.66 GB	very large, extremely low quality loss - not recommended

Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.

How to download GGUF files

Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.

The following clients/libraries will automatically download models for you, providing a list of available models to choose from:

• LM Studio
• LoLLMS Web UI
• Faraday.dev

In text-generation-webui

Under Download Model, you can enter the model repo: TheBloke/MAmmoTH-7B-GGUF and below it, a specific filename to download, such as: mammoth-7b.Q4_K_M.gguf.

Then click Download.

On the command line, including multiple files at once

I recommend using the huggingface-hub Python library:

pip3 install huggingface-hub

Then you can download any individual model file to the current directory, at high speed, with a command like this:

huggingface-cli download TheBloke/MAmmoTH-7B-GGUF mammoth-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

More advanced huggingface-cli download usage

You can also download multiple files at once with a pattern:

huggingface-cli download TheBloke/MAmmoTH-7B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'

For more documentation on downloading with huggingface-cli, please see: HF -> Hub Python Library -> Download files -> Download from the CLI.

To accelerate downloads on fast connections (1Gbit/s or higher), install hf_transfer:

pip3 install hf_transfer

And set environment variable HF_HUB_ENABLE_HF_TRANSFER to 1:

HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/MAmmoTH-7B-GGUF mammoth-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

Windows Command Line users: You can set the environment variable by running set HF_HUB_ENABLE_HF_TRANSFER=1 before the download command.

Example llama.cpp command

Make sure you are using llama.cpp from commit d0cee0d or later.

./main -ngl 32 -m mammoth-7b.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:"

Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.

Change -c 4096 to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.

If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins

For other parameters and how to use them, please refer to the llama.cpp documentation

How to run in text-generation-webui

Further instructions here: text-generation-webui/docs/llama.cpp.md.

How to run from Python code

You can use GGUF models from Python using the llama-cpp-python or ctransformers libraries.

How to load this model in Python code, using ctransformers

First install the package

Run one of the following commands, according to your system:

# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers

Simple ctransformers example code

from ctransformers import AutoModelForCausalLM

# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/MAmmoTH-7B-GGUF", model_file="mammoth-7b.Q4_K_M.gguf", model_type="llama", gpu_layers=50)

print(llm("AI is going to"))

How to use with LangChain

Here are guides on using llama-cpp-python and ctransformers with LangChain:

• LangChain + llama-cpp-python
• LangChain + ctransformers

Discord

For further support, and discussions on these models and AI in general, join us at:

TheBloke AI's Discord server

Thanks, and how to contribute

Thanks to the chirper.ai team!

Thanks to Clay from gpus.llm-utils.org!

I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.

If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.

Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.

• Patreon: https://patreon.com/TheBlokeAI
• Ko-Fi: https://ko-fi.com/TheBlokeAI

Special thanks to: Aemon Algiz.

Patreon special mentions: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: TIGER-Lab's MAmmoTH 7B

🦣 MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning

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

Paper: https://arxiv.org/pdf/2309.05653.pdf

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

Introduction

We introduce 🦣 MAmmoTH, a series of open-source large language models (LLMs) specifically tailored for general math problem-solving. The MAmmoTH models are trained on 🤗 MathInstruct Dataset, a meticulously curated instruction tuning dataset that is lightweight yet generalizable. MathInstruct is compiled from 13 math rationale datasets, six of which are newly curated by this work. It uniquely focuses on the hybrid use of chain-of-thought (CoT) and program-of-thought (PoT) rationales, and ensures extensive coverage of diverse mathematical fields.

	Base Model: Llama-2	Base Model: Code Llama
7B	🦣 MAmmoTH-7B	🦣 MAmmoTH-Coder-7B
13B	🦣 MAmmoTH-13B	🦣 MAmmoTH-Coder-13B
34B	-	🦣 MAmmoTH-Coder-34B
70B	🦣 MAmmoTH-70B	-

                                                                  |

Training Data

The models are trained on the 🤗 MathInstruct Dataset, which is compiled from 13 different math rationale datasets. Check out the dataset card for more details.

Training Procedure

The models are fine-tuned with the MathInstruct dataset using the original Llama-2 and Code Llama 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	Size	Base	GSM8K	MATH	AQuA	NumGLUE	IID Avg	SVAMP	Mathematics	SimulEq	SAT-Math	MMLU-Math	OOD Avg
MAmmoTH	7B	Llama-2	51.7	31.2	42.9	53.1	44.7	66.7	44.8	42	36.4	38.6	45.7
MAmmoTH-Coder	7B	Code-Llama	58.8	35.2	43	57.1	48.5	71.1	53.9	44.6	40	40.5	50.2
MAmmoTH	13B	Llama-2	61.7	36	44.8	59.6	50.5	72.4	48.7	40.5	42.7	45.3	49.9
MAmmoTH-Coder	13B	Code-Llama	64.3	38.6	46.1	54.2	50.8	73.2	60	44.1	40.9	45.2	52.6
MAmmoTH-Coder	34B	Code-Llama	72.3	46.8	50.8	59.6	57.3	84	64.7	50.6	51.8	50.2	60.3
MAmmoTH	70B	Llama-2	76.7	44.2	61.4	64.3	61.7	81.7	55.3	45.3	58.6	52.3	58.6

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/MAmmoTH

Prompt Format

If you want to do CoT:

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{instruction}

### Response:

If you want to do PoT:

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{instruction} Let's write a program.

### Response:

Intended Uses

These models are trained for research purposes. They are designed to solve general math problems. They can be used in educational software, tutoring systems, or any application where a solution to a math problem is needed. The models can generate both a chain of thought (CoT) rationale and a program of thought (PoT) rationale, providing a comprehensive solution to a given math problem.

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{yue2023mammoth,
  title={MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning},
  author={Xiang Yue, Xingwei Qu, Ge Zhang, Yao Fu, Wenhao Huang, Huan Sun, Yu Su, Wenhu Chen},
  journal={arXiv preprint arXiv:2309.05653},
  year={2023}
}