Want to contribute? TheBloke's Patreon page

Jon Durbin's Airoboros MPT 30B GPT4 1.4 GGML

These files are GGML format model files for Jon Durbin's Airoboros MPT 30B GPT4 1.4.

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

Prompt template

A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. 
USER: prompt
ASSISTANT:

A note regarding context length: 8K

The base model has an 8K context length. 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

Provided files

Name	Quant method	Bits	Size	Max RAM required	Use case
airoboros-mpt-30b-gpt4.ggmlv0.q4_0.bin	q4_0	4	16.85 GB	19.35 GB	Original llama.cpp quant method, 4-bit.
airoboros-mpt-30b-gpt4.ggmlv0.q4_1.bin	q4_1	4	18.73 GB	21.23 GB	Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.
airoboros-mpt-30b-gpt4.ggmlv0.q5_0.bin	q5_0	5	20.60 GB	23.10 GB	Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference.
airoboros-mpt-30b-gpt4.ggmlv0.q5_1.bin	q5_1	5	22.47 GB	24.97 GB	Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference.
airoboros-mpt-30b-gpt4.ggmlv0.q8_0.bin	q8_0	8	31.83 GB	34.33 GB	Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users.

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

Thank you to all my generous patrons and donaters!

Original model card: Jon Durbin's Airoboros MPT 30B GPT4 1.4

Technical info

This is a test of qlora fine-tuning of the mpt-30b model, with 5 epochs.

qlora compatible model: https://huggingface.co/jondurbin/mpt-30b-qlora-compatible

My fork of qlora with mpt-30b support: https://github.com/jondurbin/qlora

Differences in the qlora scripts:

requires adding --mpt True for mpt-based models
uses --num_train_epochs instead of --max_steps
uses airoboros prompt format (mostly 1:1 with vicuna) rather than alpaca, and expects an input file in JSONL format with "instruction" and "response"

I think there's a bug in gradient accumulation, so if you try this, maybe set gradient accumulation steps to 1

See the mpt-30b-qlora-compatible model card for training details.

This doesn't seem as high quality as the llama-33b versions unfortunately, with one-off tests, but I don't have a great answer as to why. Perhaps there are fewer forward layers that can be tuned?

Overview

This is mostly an extension of the previous gpt-4 series, but it's the first with mpt-30b as the base, and with a few extras:

fixed (+ more examples of) multi-character, multi-turn conversations
coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed
more roleplay examples
jokes
riddles
all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT)

This model was fine-tuned with a fork of qlora

The prompt it was trained with was:

A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. USER: [prompt] ASSISTANT:

So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).

Usage

To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a --no-history option to prevent input tokenization errors.

pip install git+https://github.com/jondurbin/FastChat

Be sure you are pulling the latest branch!

Then, you can invoke it like so (after downloading the model):

python -m fastchat.serve.cli \
  --model-path airoboros-mpt-30b-gpt4-1p4-five-epochs \
  --temperature 0.5 \
  --max-new-tokens 2048 \
  --no-history

For multi-turn conversations and chatting, you'll want to remove the --no-history option.

Context obedient question answering

By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.

The format for a closed-context prompt is as follows:

BEGININPUT
BEGINCONTEXT
url: https://some.web.site/123
date: 2023-06-01
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s).  The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION

It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.

The only prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!

I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.

BEGININPUT - denotes a new input block
BEGINCONTEXT - denotes the block of context (metadata key/value pairs) to associate with the current input block
ENDCONTEXT - denotes the end of the metadata block for the current input
[text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
ENDINPUT - denotes the end of the current input block
[repeat as many input blocks in this format as you want]
BEGININSTRUCTION - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
[instruction(s)]
ENDINSTRUCTION - denotes the end of instruction set

It sometimes works without ENDINSTRUCTION, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.

Here's a trivial, but important example to prove the point:

BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries?  Source?
ENDINSTRUCTION

And the response:

Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123

The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described:

USER: BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries?  Source?
ENDINSTRUCTION
 ASSISTANT:

Coding

You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt):

Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate

Or:

Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.

You can optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:

Write a websocket application in node.js. PLAINFORMAT

Word games / trivia

USER: This anagram of "silent" is what you do when paying attention and hearing someone.
ASSISTANT: listen

USER: Give me a list of 7 words that start with EN
ASSISTANT: 1. Endlessly
2. Enthusiastically
3. Enormously
4. Enveloping
5. Enduring
6. Enlightening
7. Encouraging

Multiple choice

USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt?

A) Mercury
B) Venus
C) Pluto
D) Jupiter
ASSISTANT: C, Pluto

Writing

Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.

Response:

ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home.

Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes.

No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice.

So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary>

Jokes

USER: Tell me a joke about bananas.
ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E.

Riddles (not great, but slightly better)

USER: What has a neck but no head?
ASSISTANT: A bottle.

Multi-character conversations

USER: Characters:
 - Yoda, the ever clever jedi master.
 - Homer Simpson, you know, the goofy yellow guy.
 - USER/Jon - don't generate any speech or actions on behalf of Jon

Rules:
 - be sure to use the manerisms and speaking style of the characters correctly
 - surround character actions with asterisks
 - always put quotes around words spoken by the characters
 - use a new line for each character's actions or speech
 - always prefix actions/speech with the character's name and colon
 - only generate text and actions on behalf of Yoda or Homer, and never anyone else

Conversation will revolve around the grapes, in a local cafe with delicious coffee.

Generate a single interaction between Yoda and Homer to start, with one sentence each.
ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer."

Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!"
USER: *enters the cafe* Sorry I'm late guys!
ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes."

Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!"

*Yoda raises an eyebrow*

License and usage

This is a real gray area, here's why:

the dataset was generated with gpt-4, via https://github.com/jondurbin/airoboros
the ToS for openai API usage has a clause preventing the output from being used to train a model that competes with OpenAI
- what does compete actually mean here?
- a 30b parameter model isn't anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place
- if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works
the training data used in essentially all large language models includes a significant of copyrighted or otherwise unallowable licensing in the first place
other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2

I am purposingly not placing a license on here because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly. Your best bet is probably to avoid using this commercially, especially since it didn't perform quite as well as expected using qlora.

TheBloke
/

airoboros-mpt-30b-gpt4-1p4-GGML