metadata

license: cc-by-sa-3.0
datasets:
  - mosaicml/dolly_hhrlhf
tags:
  - Composer
  - MosaicML
  - llm-foundry
inference: false

Want to contribute? TheBloke's Patreon page

MPT-7B-Instruct GGML

This is GGML format quantised 4-bit, 5-bit and 8-bit GGML models of MosaicML's MPT-7B-Instruct.

This repo is the result of converting to GGML and quantising.

Please note that these MPT GGMLs are not compatbile with llama.cpp. Please see below for a list of tools known to work with these model files.

Repositories available

Provided files

Name	Quant method	Bits	Size	RAM required	Use case
`mpt7b-instruct.ggmlv3.q4_0.bin`	q4_0	4bit	4.16GB	6.2GB	4-bit.
`mpt7b-instruct.ggmlv3.q4_1.bin`	q4_0	4bit	4.99GB	7.2GB	4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.
`mpt7b-instruct.ggmlv3.q5_0.bin`	q5_0	5bit	4.57GB	6.8GB	5-bit. Higher accuracy, higher resource usage and slower inference.
`mpt7b-instruct.ggmlv3.q5_1.bin`	q5_1	5bit	4.99GB	7.2GB	5-bit. Even higher accuracy, and higher resource usage and slower inference.
`mpt7b-instruct.ggmlv3.q8_0.bin`	q8_0	8bit	7.48GB	9.7GB	8-bit. Almost indistinguishable from float16. Huge resource use and slow. Not recommended for normal use.
`mpt7b-instruct.ggmlv3.fp16.bin`	fp16	16bit	13.30GB	16GB	Full 16-bit.

Compatibilty

These files are not compatible with llama.cpp.

Currently they can be used with:

KoboldCpp, a powerful inference engine based on llama.cpp, with good UI: KoboldCpp
The ctransformers Python library, which includes LangChain support: ctransformers
The GPT4All-UI which uses ctransformers: GPT4All-UI
rustformers' llm
The example mpt binary provided with ggml

As other options become available I will endeavour to update them here (do let me know in the Community tab if I've missed something!)

Tutorial for using GPT4All-UI

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!

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

Patreon special mentions: Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.

Thank you to all my generous patrons and donaters!

MPT-7B-Instruct

MPT-7B-Instruct is a model for short-form instruction following. It is built by finetuning MPT-7B on a dataset derived from the Databricks Dolly-15k and the Anthropic Helpful and Harmless (HH-RLHF) datasets.

License: CC-By-SA-3.0
Demo on Hugging Face Spaces

This model was trained by MosaicML and follows a modified decoder-only transformer architecture.

Model Date

May 5, 2023

Model License

CC-By-SA-3.0

Documentation

Blog post: Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs
Codebase (mosaicml/llm-foundry repo)
Questions: Feel free to contact us via the MosaicML Community Slack!

Example Question/Instruction

Longboi24:

What is a quoll?

MPT-7B-Instruct:

A Quoll (pronounced “cool”) is one of Australia’s native carnivorous marsupial mammals, which are also known as macropods or wallabies in other parts around Asia and South America

How to Use

Note: This model requires that trust_remote_code=True be passed to the from_pretrained method. This is because we use a custom model architecture that is not yet part of the transformers package.

It includes options for many training efficiency features such as FlashAttention (Dao et al. 2022), ALiBi, QK LayerNorm, and more.

import transformers
model = transformers.AutoModelForCausalLM.from_pretrained(
  'mosaicml/mpt-7b-instruct',
  trust_remote_code=True
)

Note: This model requires that trust_remote_code=True be passed to the from_pretrained method. This is because we use a custom MPT model architecture that is not yet part of the Hugging Face transformers package. MPT includes options for many training efficiency features such as FlashAttention, ALiBi, QK LayerNorm, and more.

To use the optimized triton implementation of FlashAttention, you can load the model with attn_impl='triton' and move the model to bfloat16:

config = transformers.AutoConfig.from_pretrained(
  'mosaicml/mpt-7b-instruct',
  trust_remote_code=True
)
config.attn_config['attn_impl'] = 'triton'

model = transformers.AutoModelForCausalLM.from_pretrained(
  'mosaicml/mpt-7b-instruct',
  config=config,
  torch_dtype=torch.bfloat16,
  trust_remote_code=True
)
model.to(device='cuda:0')

Although the model was trained with a sequence length of 2048, ALiBi enables users to increase the maximum sequence length during finetuning and/or inference. For example:

config = transformers.AutoConfig.from_pretrained(
  'mosaicml/mpt-7b-instruct',
  trust_remote_code=True
)
config.update({"max_seq_len": 4096})
model = transformers.AutoModelForCausalLM.from_pretrained(
  'mosaicml/mpt-7b-instruct',
  config=config,
  trust_remote_code=True
)

This model was trained with the EleutherAI/gpt-neox-20b tokenizer.

from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neox-20b")

Model Description

The architecture is a modification of a standard decoder-only transformer.

The model has been modified from a standard transformer in the following ways:

It uses FlashAttention
It uses ALiBi (Attention with Linear Biases) and does not use positional embeddings
It does not use biases

Hyperparameter	Value
n_parameters	6.7B
n_layers	32
n_heads	32
d_model	4096
vocab size	50432
sequence length	2048

PreTraining Data

For more details on the pretraining process, see MPT-7B.

The data was tokenized using the EleutherAI/gpt-neox-20b tokenizer.

Limitations and Biases

The following language is modified from EleutherAI's GPT-NeoX-20B

MPT-7B-Instruct can produce factually incorrect output, and should not be relied on to produce factually accurate information. MPT-7B-Instruct was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.

Acknowledgements

This model was finetuned by Sam Havens and the MosaicML NLP team

MosaicML Platform

If you're interested in training and deploying your own MPT or LLMs on the MosaicML Platform, sign up here.

Disclaimer

The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.

Citation

Please cite this model using the following format:

@online{MosaicML2023Introducing,
    author    = {MosaicML NLP Team},
    title     = {Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs},
    year      = {2023},
    url       = {www.mosaicml.com/blog/mpt-7b},
    note      = {Accessed: 2023-03-28}, % change this date
    urldate   = {2023-03-28} % change this date
}