Hugging Face's logo

TheBloke
/
Marcoroni-70B-GGUF

Text Generation
Transformers
GGUF
English
llama
text-generation-inference
Model card Files Community
1
Marcoroni-70B-GGUF / README.md
TheBloke's picture
TheBloke
Upload README.md
ad19511
preview code
|
raw
history blame
No virus
17.3 kB
metadata
base_model: https://huggingface.co/AIDC-ai-business/Marcoroni-70b
datasets:
  - Open-Orca/OpenOrca
inference: false
language:
  - en
license: cc-by-nc-4.0
model_creator: AIDC-ai-business
model_name: Marcoroni 70B
model_type: llama
pipeline_tag: text-generation
quantized_by: TheBloke
TheBlokeAI

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)

Marcoroni 70B - GGUF

Description

This repo contains GGUF format model files for AIDC-ai-business's Marcoroni 70B.

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. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible.

Here is an incomplate 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

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 cc-by-nc-4.0, 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: AIDC-ai-business's Marcoroni 70B.

Compatibility

These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit d0cee0d36d5be95a0d9088b674dbb27354107221

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
marcoroni-70b.Q2_K.gguf Q2_K 2 29.28 GB 31.78 GB smallest, significant quality loss - not recommended for most purposes
marcoroni-70b.Q3_K_S.gguf Q3_K_S 3 29.92 GB 32.42 GB very small, high quality loss
marcoroni-70b.Q3_K_M.gguf Q3_K_M 3 33.19 GB 35.69 GB very small, high quality loss
marcoroni-70b.Q3_K_L.gguf Q3_K_L 3 36.15 GB 38.65 GB small, substantial quality loss
marcoroni-70b.Q4_0.gguf Q4_0 4 38.87 GB 41.37 GB legacy; small, very high quality loss - prefer using Q3_K_M
marcoroni-70b.Q4_K_S.gguf Q4_K_S 4 39.07 GB 41.57 GB small, greater quality loss
marcoroni-70b.Q4_K_M.gguf Q4_K_M 4 41.42 GB 43.92 GB medium, balanced quality - recommended
marcoroni-70b.Q5_0.gguf Q5_0 5 47.46 GB 49.96 GB legacy; medium, balanced quality - prefer using Q4_K_M
marcoroni-70b.Q5_K_S.gguf Q5_K_S 5 47.46 GB 49.96 GB large, low quality loss - recommended
marcoroni-70b.Q5_K_M.gguf Q5_K_M 5 48.75 GB 51.25 GB large, very low quality loss - recommended
marcoroni-70b.Q6_K.gguf Q6_K 6 56.59 GB 59.09 GB very large, extremely low quality loss
marcoroni-70b.Q8_0.gguf Q8_0 8 73.29 GB 75.79 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.

Q6_K and Q8_0 files are split and require joining

Note: HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files.

Click for instructions regarding Q6_K and Q8_0 files

q6_K

Please download:

  • marcoroni-70b.Q6_K.gguf-split-a
  • marcoroni-70b.Q6_K.gguf-split-b

q8_0

Please download:

  • marcoroni-70b.Q8_0.gguf-split-a
  • marcoroni-70b.Q8_0.gguf-split-b

To join the files, do the following:

Linux and macOS:

cat marcoroni-70b.Q6_K.gguf-split-* > marcoroni-70b.Q6_K.gguf && rm marcoroni-70b.Q6_K.gguf-split-*
cat marcoroni-70b.Q8_0.gguf-split-* > marcoroni-70b.Q8_0.gguf && rm marcoroni-70b.Q8_0.gguf-split-*

Windows command line:

COPY /B marcoroni-70b.Q6_K.gguf-split-a + marcoroni-70b.Q6_K.gguf-split-b marcoroni-70b.Q6_K.gguf
del marcoroni-70b.Q6_K.gguf-split-a marcoroni-70b.Q6_K.gguf-split-b

COPY /B marcoroni-70b.Q8_0.gguf-split-a + marcoroni-70b.Q8_0.gguf-split-b marcoroni-70b.Q8_0.gguf
del marcoroni-70b.Q8_0.gguf-split-a marcoroni-70b.Q8_0.gguf-split-b

Example llama.cpp command

Make sure you are using llama.cpp from commit d0cee0d36d5be95a0d9088b674dbb27354107221 or later.

./main -ngl 32 -m marcoroni-70b.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:"

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

Change -c 4096 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 from Python using ctransformers

First install the package 

# Base ctransformers with no GPU acceleration
pip install ctransformers>=0.2.24
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]>=0.2.24
# Or with ROCm GPU acceleration
CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems
CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers

Simple example code to load one of these GGUF models 

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/Marcoroni-70B-GGUF", model_file="marcoroni-70b.q4_K_M.gguf", model_type="llama", gpu_layers=50)

print(llm("AI is going to"))

How to use with LangChain

Here's guides on using llama-cpp-python or ctransformers with LangChain:

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.

Special thanks to: Aemon Algiz.

Patreon special mentions: Russ Johnson, J, alfie_i, Alex, NimbleBox.ai, Chadd, Mandus, Nikolai Manek, Ken Nordquist, ya boyyy, Illia Dulskyi, Viktor Bowallius, vamX, Iucharbius, zynix, Magnesian, Clay Pascal, Pierre Kircher, Enrico Ros, Tony Hughes, Elle, Andrey, knownsqashed, Deep Realms, Jerry Meng, Lone Striker, Derek Yates, Pyrater, Mesiah Bishop, James Bentley, Femi Adebogun, Brandon Frisco, SuperWojo, Alps Aficionado, Michael Dempsey, Vitor Caleffi, Will Dee, Edmond Seymore, usrbinkat, LangChain4j, Kacper Wikieł, Luke Pendergrass, John Detwiler, theTransient, Nathan LeClaire, Tiffany J. Kim, biorpg, Eugene Pentland, Stanislav Ovsiannikov, Fred von Graf, terasurfer, Kalila, Dan Guido, Nitin Borwankar, 阿明, Ai Maven, John Villwock, Gabriel Puliatti, Stephen Murray, Asp the Wyvern, danny, Chris Smitley, ReadyPlayerEmma, S_X, Daniel P. Andersen, Olakabola, Jeffrey Morgan, Imad Khwaja, Caitlyn Gatomon, webtim, Alicia Loh, Trenton Dambrowitz, Swaroop Kallakuri, Erik Bjäreholt, Leonard Tan, Spiking Neurons AB, Luke @flexchar, Ajan Kanaga, Thomas Belote, Deo Leter, RoA, Willem Michiel, transmissions 11, subjectnull, Matthew Berman, Joseph William Delisle, David Ziegler, Michael Davis, Johann-Peter Hartmann, Talal Aujan, senxiiz, Artur Olbinski, Rainer Wilmers, Spencer Kim, Fen Risland, Cap'n Zoog, Rishabh Srivastava, Michael Levine, Geoffrey Montalvo, Sean Connelly, Alexandros Triantafyllidis, Pieter, Gabriel Tamborski, Sam, Subspace Studios, Junyu Yang, Pedro Madruga, Vadim, Cory Kujawski, K, Raven Klaugh, Randy H, Mano Prime, Sebastain Graf, Space Cruiser

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: AIDC-ai-business's Marcoroni 70B

Marcoroni-70B

Fine-tuned from Llama-2-70B，we use Orca-style data and other open source data for fine-tuning.

Model Details

  • Trained by: trained by AIDC AI-Business.
  • Model type: Marcoroni-70B is an auto-regressive language model based on the Llama 2 transformer architecture.
  • Language(s): English
  • License for Marcoroni-70B base weights: Non-Commercial Creative Commons license (CC BY-NC-4.0)

Prompting

Prompt Template for alpaca style 

### Instruction:

<prompt> (without the <>)

### Response:

Our Other Projects:

Evulation Results (Open LLM Leaderboard)

Metric Value
Avg. 73.94
ARC (25-shot) 72.95
HellaSwag (10-shot) 87.51
MMLU (5-shot) 70.79
TruthfulQA (0-shot) 64.49