Chat & support: my new Discord server

Want to contribute? TheBloke's Patreon page

MosaicML's MPT-30B-Chat GGML

These files are GGML format model files for MosaicML's MPT-30B-Chat .

Please note that these GGMLs are not compatible with llama.cpp, or currently with text-generation-webui . Please see below for a list of tools known to work with these model files.

KoboldCpp just added GPU accelerated (OpenCL) support for MPT models, so that is the client I recommend using for these models.

Note : Please make sure you're using KoboldCpp version 1.32.3 or later, as a number of MPT-related bugs are fixed.

Repositories available

• 2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference
• Unquantised fp16 model in pytorch format, for GPU inference and for further conversions

Prompt template

Based on the code for the MPT 30B Chat Space, I believe this is the correct prompt template:

<|im_start|>system
A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.<|im_end|>
<|im_start|>user
prompt goes here<|im_end|>
<|im_start|>assistant

A note regarding context length: 8K

The base model has an 8K context length. It is not yet confirmed if the 8K context of this model works with the quantised files.

If it does, KoboldCpp supports 8K context if you manually set it to 8K by adjusting the text box above the slider:

It is currently unknown as to increased context is compatible with other MPT GGML clients.

If you have feedback on this, please let me know.

Compatibilty

These files are not compatible with text-generation-webui, llama.cpp, or llama-cpp-python.

Currently they can be used with:

• KoboldCpp, a powerful inference engine based on llama.cpp, with good UI and GPU accelerated support for MPT models: KoboldCpp
• The ctransformers Python library, which includes LangChain support: ctransformers
• The LoLLMS Web UI which uses ctransformers: LoLLMS Web 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 LoLLMS Web UI

• Text tutorial, written by Lucas3DCG
• Video tutorial, by LoLLMS Web UI's author ParisNeo

Provided files

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.

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

Special thanks to : Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.

Patreon special mentions : Mano Prime, Fen Risland, Derek Yates, Preetika Verma, webtim, Sean Connelly, Alps Aficionado, Karl Bernard, Junyu Yang, Nathan LeClaire, Chris McCloskey, Lone Striker, Asp the Wyvern, Eugene Pentland, Imad Khwaja, trip7s trip, WelcomeToTheClub, John Detwiler, Artur Olbinski, Khalefa Al-Ahmad, Trenton Dambrowitz, Talal Aujan, Kevin Schuppel, Luke Pendergrass, Pyrater, Joseph William Delisle, terasurfer , vamX, Gabriel Puliatti, David Flickinger, Jonathan Leane, Iucharbius , Luke, Deep Realms, Cory Kujawski, ya boyyy, Illia Dulskyi, senxiiz, Johann-Peter Hartmann, John Villwock, K, Ghost , Spiking Neurons AB, Nikolai Manek, Rainer Wilmers, Pierre Kircher, biorpg, Space Cruiser, Ai Maven, subjectnull, Willem Michiel, Ajan Kanaga, Kalila, chris gileta, Oscar Rangel.

Thank you to all my generous patrons and donaters!

Original model card: MosaicML's MPT-30B-chat

MPT-30B-Chat

MPT-30B-Chat is a chatbot-like model for dialogue generation. It was built by finetuning MPT-30B on the ShareGPT-Vicuna , Camel-AI , GPTeacher , Guanaco , Baize and some generated datasets.

• License: CC-By-NC-SA-4.0 (non-commercial use only)
• Demo on Hugging Face Spaces

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

Model Date

June 22, 2023

Model License

CC-By-NC-SA-4.0 (non-commercial use only)

Documentation

• Blog post: Raising the bar for open-source foundation models
• Codebase (mosaicml/llm-foundry repo)
• Questions: Feel free to contact us via the MosaicML Community Slack !

Example Dialogue

ksreenivasan :

I want you to come up with a tweet based on this summary of the article:

We are excited to extend the MosaicML Foundation Series with MPT-30B, a new commercially licensed open-source model that is significantly more powerful, and outperforms the original GPT-3. In addition, we are releasing two fine-tuned models, MPT-30B-Instruct and MPT-30B-Chat, that are built on top of MPT-30B and excel at short-form instruction following and multi-turn conversations, respectively. All MPT-30B models come with special features that differentiate them from other LLMs, including an 8k token context window (which can be further extended via finetuning; see MPT-7B-StoryWriter), support for context-length extrapolation via ALiBi, and efficient inference + training performance via FlashAttention. It also has strong coding abilities thanks to its pretraining data mixture.

MPT-30B-Chat :

"Revolutionize your AI capabilities with MosaicML's latest addition, MPT-30B! Outperforming GPT-3, this open-source model is significantly more powerful and comes with finely-tuned models for exceptional instruction following and multi-turn conversations. Unleash the potential of an 8k token context window, ALiBi support, and FlashAttention. Experience the future of AI with MosaicML! #AI #ML #innovation"

ksreenivasan :

Is there anything you want to say to MosaicML about this exciting news?

MPT-30B-Chat :

As your AI marketing assistant, I would say that this is truly exciting news for the AI community! MosaicML's latest addition, MPT-30B, is poised to revolutionize the industry with its powerful open-source capabilities and finely-tuned models for instruction following and multi-turn conversations. The special features, including the 8k token context window, ALiBi support, and FlashAttention, are sure to set MosaicML's MPT-30B apart from other LLMs. Congratulations to the MosaicML team on this incredible achievement!

How to Use

This model is best used with the MosaicML llm-foundry repository for training and finetuning.

import transformers
model = transformers.AutoModelForCausalLM.from_pretrained(
  'mosaicml/mpt-30b-chat',
  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 on GPU ( cuda:0 ) with attn_impl='triton' and with bfloat16 precision:

import torch
import transformers

name = 'mosaicml/mpt-30b-chat'

config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
config.attn_config['attn_impl'] = 'triton'  # change this to use triton-based FlashAttention
config.init_device = 'cuda:0' # For fast initialization directly on GPU!

model = transformers.AutoModelForCausalLM.from_pretrained(
  name,
  config=config,
  torch_dtype=torch.bfloat16, # Load model weights in bfloat16
  trust_remote_code=True
)

The model was trained initially with a sequence length of 4096 with an additional pretraining stage for sequence length adapation up to 8192. However, ALiBi enables users to increase the maximum sequence length even further during finetuning and/or inference. For example:

import transformers

name = 'mosaicml/mpt-30b-chat'

config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
config.max_seq_len = 16384 # (input + output) tokens can now be up to 16384

model = transformers.AutoModelForCausalLM.from_pretrained(
  name,
  config=config,
  trust_remote_code=True
)

This model was trained with the MPT-30B tokenizer which is based on the EleutherAI/gpt-neox-20b tokenizer and includes additional padding and eos tokens.

from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('mosaicml/mpt-30b')

The model can then be used, for example, within a text-generation pipeline. Note: when running Torch modules in lower precision, it is best practice to use the torch.autocast context manager .

from transformers import pipeline

with torch.autocast('cuda', dtype=torch.bfloat16):
    inputs = tokenizer('Here is a recipe for vegan banana bread:\n', return_tensors="pt").to('cuda')
    outputs = model.generate(**inputs, max_new_tokens=100)
    print(tokenizer.batch_decode(outputs, skip_special_tokens=True))

# or using the HF pipeline
pipe = pipeline('text-generation', model=model, tokenizer=tokenizer, device='cuda:0')
with torch.autocast('cuda', dtype=torch.bfloat16):
    print(
        pipe('Here is a recipe for vegan banana bread:\n',
            max_new_tokens=100,
            do_sample=True,
            use_cache=True))

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

Data Mix

The model was trained on the following data mix:

"LongConversations" is a GPT3.5/4-generated dataset, details of which will be released at a later date.

Training Configuration

This model was trained on 64 H100s for about 7.6 hours using the MosaicML Platform . The model was trained with sharded data parallelism using FSDP and used the AdamW optimizer.

Limitations and Biases

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

MPT-30B-Chat can produce factually incorrect output, and should not be relied on to produce factually accurate information. MPT-30B-Chat 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

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 consult an attorney before using this model for commercial purposes.

MosaicML Platform

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

Citation

Please cite this model using the following format:

@online{MosaicML2023Introducing,
    author    = {MosaicML NLP Team},
    title     = {Introducing MPT-30B: Raising the bar
for open-source foundation models},
    year      = {2023},
    url       = {www.mosaicml.com/blog/mpt-30b},
    note      = {Accessed: 2023-06-22},
    urldate   = {2023-06-22}
}