TheBloke/MAmmoTH-Coder-13B-GPTQ

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 Coder 13B - GPTQ

• Model creator: TIGER-Lab
• Original model: MAmmoTH Coder 13B

Description

This repo contains GPTQ model files for TIGER-Lab's MAmmoTH Coder 13B.

Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.

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 Coder 13B.

Provided files, and GPTQ parameters

Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.

Each separate quant is in a different branch. See below for instructions on fetching from different branches.

All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches are made with AutoGPTQ. Files in the main branch which were uploaded before August 2023 were made with GPTQ-for-LLaMa.

Explanation of GPTQ parameters

• Bits: The bit size of the quantised model.
• GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
• Act Order: True or False. Also known as desc_act. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
• Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
• GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
• Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
• ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.

Branch	Bits	GS	Act Order	Damp %	GPTQ Dataset	Seq Len	Size	ExLlama	Desc
main	4	128	Yes	0.1	Evol Instruct Code	4096	7.26 GB	Yes	4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy.
gptq-4-32g-actorder_True	4	32	Yes	0.1	Evol Instruct Code	4096	8.00 GB	Yes	4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage.
gptq-8--1g-actorder_True	8	None	Yes	0.1	Evol Instruct Code	4096	13.36 GB	No	8-bit, with Act Order. No group size, to lower VRAM requirements.
gptq-8-128g-actorder_True	8	128	Yes	0.1	Evol Instruct Code	4096	13.65 GB	No	8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy.
gptq-8-32g-actorder_True	8	32	Yes	0.1	Evol Instruct Code	4096	14.55 GB	No	8-bit, with group size 32g and Act Order for maximum inference quality.
gptq-4-64g-actorder_True	4	64	Yes	0.1	Evol Instruct Code	4096	7.51 GB	Yes	4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy.

How to download, including from branches

In text-generation-webui

To download from the main branch, enter TheBloke/MAmmoTH-Coder-13B-GPTQ in the "Download model" box.

To download from another branch, add :branchname to the end of the download name, eg TheBloke/MAmmoTH-Coder-13B-GPTQ:gptq-4-32g-actorder_True

From the command line

I recommend using the huggingface-hub Python library:

pip3 install huggingface-hub

To download the main branch to a folder called MAmmoTH-Coder-13B-GPTQ:

mkdir MAmmoTH-Coder-13B-GPTQ
huggingface-cli download TheBloke/MAmmoTH-Coder-13B-GPTQ --local-dir MAmmoTH-Coder-13B-GPTQ --local-dir-use-symlinks False

To download from a different branch, add the --revision parameter:

mkdir MAmmoTH-Coder-13B-GPTQ
huggingface-cli download TheBloke/MAmmoTH-Coder-13B-GPTQ --revision gptq-4-32g-actorder_True --local-dir MAmmoTH-Coder-13B-GPTQ --local-dir-use-symlinks False

More advanced huggingface-cli download usage

If you remove the --local-dir-use-symlinks False parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: ~/.cache/huggingface), and symlinks will be added to the specified --local-dir, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.

The cache location can be changed with the HF_HOME environment variable, and/or the --cache-dir parameter to huggingface-cli.

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:

mkdir MAmmoTH-Coder-13B-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/MAmmoTH-Coder-13B-GPTQ --local-dir MAmmoTH-Coder-13B-GPTQ --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.

With git (not recommended)

To clone a specific branch with git, use a command like this:

git clone --single-branch --branch gptq-4-32g-actorder_True https://huggingface.co/TheBloke/MAmmoTH-Coder-13B-GPTQ

Note that using Git with HF repos is strongly discouraged. It will be much slower than using huggingface-hub, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the .git folder as a blob.)

How to easily download and use this model in text-generation-webui.

Please make sure you're using the latest version of text-generation-webui.

It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.

1. Click the Model tab.
2. Under Download custom model or LoRA, enter TheBloke/MAmmoTH-Coder-13B-GPTQ.

• To download from a specific branch, enter for example TheBloke/MAmmoTH-Coder-13B-GPTQ:gptq-4-32g-actorder_True
• see Provided Files above for the list of branches for each option.

3. Click Download.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to Model.
6. In the Model dropdown, choose the model you just downloaded: MAmmoTH-Coder-13B-GPTQ
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click Save settings for this model followed by Reload the Model in the top right.

• Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file quantize_config.json.

9. Once you're ready, click the Text Generation tab and enter a prompt to get started!

How to use this GPTQ model from Python code

Install the necessary packages

Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.

pip3 install transformers optimum
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/  # Use cu117 if on CUDA 11.7

If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:

pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
git checkout v0.4.2
pip3 install .

You can then use the following code

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

model_name_or_path = "TheBloke/MAmmoTH-Coder-13B-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4-32g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                             device_map="auto",
                                             trust_remote_code=False,
                                             revision="main")

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)

prompt = "Tell me about AI"
prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:
'''

print("\n\n*** Generate:")

input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))

# Inference can also be done using transformers' pipeline

print("*** Pipeline:")
pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    max_new_tokens=512,
    do_sample=True,
    temperature=0.7,
    top_p=0.95,
    top_k=40,
    repetition_penalty=1.1
)

print(pipe(prompt_template)[0]['generated_text'])

Compatibility

The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with Occ4m's GPTQ-for-LLaMa fork.

ExLlama is compatible with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.

Huggingface Text Generation Inference (TGI) is compatible with all GPTQ models.

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 Coder 13B

🦣 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}
}