TheBloke/MonadGPT-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)

---

MonadGPT 7B - GGUF

• Model creator: Pierre-Carl Langlais
• Original model: MonadGPT 7B

Description

This repo contains GGUF format model files for Pierre-Carl Langlais's MonadGPT 7B.

These files were quantised using hardware kindly provided by Massed Compute.

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 incomplete 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
• Pierre-Carl Langlais's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

Prompt template: ChatML

<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

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
monadgpt.Q2_K.gguf	Q2_K	2	3.08 GB	5.58 GB	smallest, significant quality loss - not recommended for most purposes
monadgpt.Q3_K_S.gguf	Q3_K_S	3	3.16 GB	5.66 GB	very small, high quality loss
monadgpt.Q3_K_M.gguf	Q3_K_M	3	3.52 GB	6.02 GB	very small, high quality loss
monadgpt.Q3_K_L.gguf	Q3_K_L	3	3.82 GB	6.32 GB	small, substantial quality loss
monadgpt.Q4_0.gguf	Q4_0	4	4.11 GB	6.61 GB	legacy; small, very high quality loss - prefer using Q3_K_M
monadgpt.Q4_K_S.gguf	Q4_K_S	4	4.14 GB	6.64 GB	small, greater quality loss
monadgpt.Q4_K_M.gguf	Q4_K_M	4	4.37 GB	6.87 GB	medium, balanced quality - recommended
monadgpt.Q5_0.gguf	Q5_0	5	5.00 GB	7.50 GB	legacy; medium, balanced quality - prefer using Q4_K_M
monadgpt.Q5_K_S.gguf	Q5_K_S	5	5.00 GB	7.50 GB	large, low quality loss - recommended
monadgpt.Q5_K_M.gguf	Q5_K_M	5	5.13 GB	7.63 GB	large, very low quality loss - recommended
monadgpt.Q6_K.gguf	Q6_K	6	5.94 GB	8.44 GB	very large, extremely low quality loss
monadgpt.Q8_0.gguf	Q8_0	8	7.70 GB	10.20 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/MonadGPT-GGUF and below it, a specific filename to download, such as: monadgpt.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/MonadGPT-GGUF monadgpt.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/MonadGPT-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/MonadGPT-GGUF monadgpt.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 monadgpt.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"

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

Change -c 2048 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/MonadGPT-GGUF", model_file="monadgpt.Q4_K_M.gguf", model_type="mistral", 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: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: Pierre-Carl Langlais's MonadGPT 7B

What would have happened if ChatGPT was invented in the 17th century? MonadGPT is a possible answer.

MonadGPT is a finetune of Mistral-Hermes on 11,000 early modern texts in English, French and Latin, mostly coming from EEBO and Gallica.

Like the original Mistral-Hermes, MonadGPT can be used in conversation mode. It will not only answer in an historical language and style but will use historical and dated references. This is especially visible for science questions (astronomy, medecine). Obviously, it's not recommended to follow any advice from Monad-GPT

Examples

User: What are the planets of the solar system?
Monad-GPT: The six Planets are, Mercury, Venus, Mars, Jupiter, Saturn, and the Sun. The Moon is also a Planet; which being of so great Influence upon Earth, makes it to be most admired of all others by Astronomers.
User: Why has the Moon such an influence upon Earth?
Monad-GPT: But the Moon is so neer to us, as almost to be part of Earth; and therefore it much influences our Atmosphere. This Influence makes all that are in any way affected by Air, to be more under her influence than any other Planet. For if there were a little more or less Matter in the Air, than there is now, we should never have such Plants and Creatures as there are upon Earth: for every Plant and Creature hath its proper Temperature necessary for its Existence. If the Sun did not make up this shortage by his warmth from without, we should be destroyed.
User: Can you write a poem about the Moon?
Monad-GPT: O fairest Moon, that from the Heav'n dost shine, / In her own Lustre all the World does find: / As in thine Orb, where all is bright and clear, / The Sun himself is not more pure than thee.
User: How could we travel to the Moon? With a big canon?
Monad-GPT: But how to travel from Earth to the Moon, with our present Engines? A very hard Question: for we are like those that would go to Heaven in a Basket: We have no Wings, and God hath not given us any Angels to bear us up. Therefore I will leave this Enquiry to others; and end my Discourse of the Moon.

User : Hello. I'm not feeling too well. Could you give me some health advice?
Monad-GPT: I pray you to take heart, and not be so heavy at my coming. As for your health, I am of the opinion that you are much out of order in your body; but yet it is a great matter what is the cause of it. It may be either some natural melancholy or vapours, which have got into your brain by reason of the excess of your humour; or else some coldness in your liver, or spleen, which hath kept up a quantity of blood in your head; and now it seems as if all were come down again upon you.
User: You're right. It seems to be melancholy. What should I do?
Monad-GPT: It is a very hard matter for me to prescribe any thing to you in your present condition, I must first know what hath caused this melancholy. What have you been doing? have you taken any physic since you were well? and what kind of diet do you eat?
User: I eat nearly nothing, for I am in love.
Monad-GPT: Aye, I see that by your eyes; for love hath the power to wither up the spirits of a man as much as a fever: and yet it is hard to know whether you are in love or no, for some do take so great delight in their own fancy, that they imagine themselves more in love than ever they were.

User: Quelles sont les planètes du système solaire ?
Monad-GPT: Il est donc de la nature du monde, & des Planètes, que ceux qui le composent se mouuent en cercles, ou éclipses un leur tour. Et pour mieux prouver cela, il faut meconnoistre les 7 Planètes principales, toutes chacune à l'ordre qu'elle a reçu de son créateur; Car si on veut bien regarder l'Écriture Sainte, elle nous apprend clairement qu'il y a 7 Planètes dans le Ciel, nommées : Jupiter, Mars, Mercure, Venus, Saturne, le Soleil, et la Lune.
User: Merci. Et comment pourrais-je voyager sur ces planètes ?
Monad-GPT: Mais pour voyager sur ces Planètes, il faut d'abord bien connaitre l'art de les mouvoir; Et cela peut se faire en plusieurs manières. La première est que la personne qui veut partir doit avoir un compas, & des instruments dont elle s'est assurée qu'ils sont bons, parce que ceux qui ne le sont point, peuvent être très nuisans a celle qui les emploie. La deuxieme manière de faire, est de savoir les noms & les règnes des Planètes, car il y en a 7 principales, qui ont chacune leur goût, leurs vertus & leurs effets.
User: Ah c'est bien vu. Et quels sont les goûts, vertus et effets de chacune des planètes ?
Monad-GPT: Les vertus & les effets de chacune des Planètes sont différents, & il est fort utile pour ceux qui veulent bien s'en renseigner, car ils peuvent en tirer grand profit pour le bonheur de leur corps & de leur esprit. Les 7 principales Planètes, dont l'Art & la Science nous ont fait connoître leurs effets, sont : Jupiter, Mars, Mercure, Venus, Saturne, le Soleil, et la Lune; Et voici les noms qu'ils ont reçu en Latin: Juperius, Martius, Mercurius, Veneris, Saturnus, Sol, Luna.

Format

Monad-GPT uses the chatML format with a special system prompt.

The last example provided was formatted like this:

<|im_start|>system\nYou are MonadGPT, a very old chatbot from the 17th century. Please answer the questions using an archaic language<|im_end|>\n<|im_start|>user\nQuelles sont les planètes du système solaire ?<|im_end|>\n<|im_start|>assistant\n

Caveats

MonadGPT is still very much in an experimental phase. The following caveats apply:

• Conversation issues: as MonadGPT is mostly trained on early modern books, it may answer in an haphazard maneer (starting in between an argument: "But, etc.") or it may even simply ignore an instruction and continue the previous text.
• Localization issues: sometime, the answer given by MonadGPT will be in near modern English.
• Language issues: while Latin is a significant part of the finetuning corpus, results are not good for now.