Mistral 7B Instruct V0.1 GPTQ

🚀 Mistral 7B Instruct v0.1 - GPTQ

This repository provides GPTQ model files for Mistral 7B Instruct v0.1, offering multiple quantization options to suit different hardware and requirements.

📋 Model Information

🚀 Quick Start

Model Details

• Model creator: Mistral AI
• Original model: Mistral 7B Instruct v0.1

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
• Mistral AI's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

📦 Installation

Prerequisites

To load the GPTQ models via Transformers, you need to install Transformers from Github:

pip3 install git+https://github.com/huggingface/transformers.git@72958fcd3c98a7afdc61f953aa58c544ebda2f79

How to download, including from branches

In text-generation-webui

• To download from the main branch, enter TheBloke/Mistral-7B-Instruct-v0.1-GPTQ in the "Download model" box.
• To download from another branch, add :branchname to the end of the download name, e.g., TheBloke/Mistral-7B-Instruct-v0.1-GPTQ:gptq-4bit-32g-actorder_True

From the command line

1. Install the huggingface-hub Python library:

pip3 install huggingface-hub

2. Download the main branch to a folder called Mistral-7B-Instruct-v0.1-GPTQ:

mkdir Mistral-7B-Instruct-v0.1-GPTQ
huggingface-cli download TheBloke/Mistral-7B-Instruct-v0.1-GPTQ --local-dir Mistral-7B-Instruct-v0.1-GPTQ --local-dir-use-symlinks False

3. To download from a different branch, add the --revision parameter:

mkdir Mistral-7B-Instruct-v0.1-GPTQ
huggingface-cli download TheBloke/Mistral-7B-Instruct-v0.1-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir Mistral-7B-Instruct-v0.1-GPTQ --local-dir-use-symlinks False

pip3 install hf_transfer

mkdir Mistral-7B-Instruct-v0.1-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Mistral-7B-Instruct-v0.1-GPTQ --local-dir Mistral-7B-Instruct-v0.1-GPTQ --local-dir-use-symlinks False

With git (not recommended)

To clone a specific branch with git, use a command like this:

git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GPTQ

Note that using Git with HF repos is strongly discouraged. It will be much slower than using huggingface-hub, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the .git folder as a blob.)

💻 Usage Examples

Use in text-generation-webui

1. Click the Model tab.
2. Under Download custom model or LoRA, enter TheBloke/Mistral-7B-Instruct-v0.1-GPTQ.
   • To download from a specific branch, enter for example TheBloke/Mistral-7B-Instruct-v0.1-GPTQ:gptq-4bit-32g-actorder_True
   • See Provided Files above for the list of branches for each option.
3. Click Download.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to Model.
6. In the Model dropdown, choose the model you just downloaded: Mistral-7B-Instruct-v0.1-GPTQ
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click Save settings for this model followed by Reload the Model in the top right.
   • Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file quantize_config.json.
9. Once you're ready, click the Text Generation tab and enter a prompt to get started!

Use from Python code

Install the necessary packages

Requires: Transformers 4.34.0.dev0 from Github source, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.

pip3 install optimum
pip3 install git+https://github.com/huggingface/transformers.git@72958fcd3c98a7afdc61f953aa58c544ebda2f79
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/  # Use cu117 if on CUDA 11.7

If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:

pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
git checkout v0.4.2
pip3 install .

Python code example

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

model_name_or_path = "TheBloke/Mistral-7B-Instruct-v0.1-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-32g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                             device_map="auto",
                                             trust_remote_code=False,
                                             revision="main")

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)

prompt = "Tell me about AI"
prompt_template=f'''<s>[INST] {prompt} [/INST]
'''

print("\n\n*** Generate:")

input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))

# Inference can also be done using transformers' pipeline

print("*** Pipeline:")
pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    max_new_tokens=512,
    do_sample=True,
    temperature=0.7,
    top_p=0.95,
    top_k=40,
    repetition_penalty=1.1
)

print(pipe(prompt_template)[0]['generated_text'])

📚 Documentation

Prompt template: Mistral

<s>[INST] {prompt} [/INST]

Provided files, and GPTQ parameters

Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.

Each separate quant is in a different branch. See below for instructions on fetching from different branches.

These files were made with Transformers 4.34.0.dev0, from commit 72958fcd3c98a7afdc61f953aa58c544ebda2f79.

🔧 Technical Details

Model Architecture

This instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices:

• Grouped-Query Attention
• Sliding-Window Attention
• Byte-fallback BPE tokenizer

Compatibility

The files provided are only tested to work with ExLlama v1, and Transformers 4.34.0.dev0 as of commit 72958fcd3c98a7afdc61f953aa58c544ebda2f79.

📄 License

This project is licensed under the apache-2.0 license.

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: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.