Hugging Face's logo

TheBloke
/
minotaur-13B-fixed-GPTQ

Text Generation
Transformers
Safetensors
llama
OpenAccess AI Collective
MPT
axolotl
text-generation-inference
4-bit precision
gptq
Model card Files Community
TheBlokeAI

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

Minotaur 13B Fixed - GPTQ

Description

This repo contains GPTQ model files for OpenAccess AI Collective's Minotaur 13B Fixed.

Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.

Repositories available

Prompt template: Vicuna 

A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:

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.

All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches are made with AutoGPTQ. Files in the main branch which were uploaded before August 2023 were made with GPTQ-for-LLaMa.

Explanation of GPTQ parameters
  • Bits: The bit size of the quantised model.
  • GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
  • Act Order: True or False. Also known as desc_act. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
  • Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
  • GPTQ dataset: The dataset used for quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
  • Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
  • ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
Branch Bits GS Act Order Damp % GPTQ Dataset Seq Len Size ExLlama Desc
main 4 128 No 0.01 wikitext 2048 7.45 GB Yes 4-bit, without Act Order and group size 128g.
gptq-4bit-32g-actorder_True 4 32 Yes 0.01 wikitext 2048 8.00 GB Yes 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage.
gptq-4bit-64g-actorder_True 4 64 Yes 0.01 wikitext 2048 7.51 GB Yes 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy.
gptq-4bit-128g-actorder_True 4 128 Yes 0.01 wikitext 2048 7.26 GB Yes 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy.
gptq-8bit--1g-actorder_True 8 None Yes 0.01 wikitext 2048 13.36 GB No 8-bit, with Act Order. No group size, to lower VRAM requirements.
gptq-8bit-128g-actorder_False 8 128 No 0.01 wikitext 2048 13.65 GB No 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed.

How to download from branches

  • In text-generation-webui, you can add :branch to the end of the download name, eg TheBloke/minotaur-13B-fixed-GPTQ:main
  • With Git, you can clone a branch with:
git clone --single-branch --branch main https://huggingface.co/TheBloke/minotaur-13B-fixed-GPTQ
  • In Python Transformers code, the branch is the revision parameter; see below.

How to easily download and use this model in text-generation-webui.

Please make sure you're using the latest version of text-generation-webui.

It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.

  1. Click the Model tab.
  2. Under Download custom model or LoRA, enter TheBloke/minotaur-13B-fixed-GPTQ.
  • To download from a specific branch, enter for example TheBloke/minotaur-13B-fixed-GPTQ:main
  • see Provided Files above for the list of branches for each option.
  1. Click Download.
  2. The model will start downloading. Once it's finished it will say "Done".
  3. In the top left, click the refresh icon next to Model.
  4. In the Model dropdown, choose the model you just downloaded: minotaur-13B-fixed-GPTQ
  5. The model will automatically load, and is now ready for use!
  6. 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.
  1. Once you're ready, click the Text Generation tab and enter a prompt to get started!

How to use this GPTQ model from Python code

Install the necessary packages

Requires: Transformers 4.32.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.

pip3 install transformers>=4.32.0 optimum>=1.12.0
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
pip3 install .

For CodeLlama models only: you must use Transformers 4.33.0 or later.

If 4.33.0 is not yet released when you read this, you will need to install Transformers from source:

pip3 uninstall -y transformers
pip3 install git+https://github.com/huggingface/transformers.git

You can then use the following code 

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

model_name_or_path = "TheBloke/minotaur-13B-fixed-GPTQ"
# To use a different branch, change revision
# For example: revision="main"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                             device_map="auto",
                                             trust_remote_code=True,
                                             revision="main")

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

prompt = "Tell me about AI"
prompt_template=f'''A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:

'''

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'])

Compatibility

The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with Occ4m's GPTQ-for-LLaMa fork.

ExLlama is compatible with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.

Huggingface Text Generation Inference (TGI) is compatible with all GPTQ models.

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

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: OpenAccess AI Collective's Minotaur 13B Fixed

Built with Axolotl 💵 Donate to OpenAccess AI Collective to help us keep building great tools and models!

Due to a bug, the initial release of Minotaur 13B dropped a few datasets during training. We have corrected the issue and this is the retrained model

The affected datasets include:

  • prose generation
  • classification
  • coding

Minotaur 13B (FIXED)

Minotaur 13B is an instruct fine-tuned model on top of LlaMA-13B. Minotaur 13B is fine-tuned on only completely open datasets making this model reproducible by anyone.

Questions, comments, feedback, looking to donate, or want to help? Reach out on our Discord or email [email protected]

Prompts

Chat only style prompts using USER:,ASSISTANT:.

minotaur

Training Datasets

Minotaur 13B model is fine-tuned on the following openly available datasets:

Shoutouts

Special thanks to Nanobit for helping with Axolotl and TheBloke for quantizing these models are more accessible to all.

Demo

HF Demo in Spaces available in the Community ChatBot Arena under the OAAIC Chatbots tab.

Release Notes

Build

Minotaur was built with Axolotl on 6XA100 80GB

  • 1 epochs taking approximately 7.5 hours

Bias, Risks, and Limitations

Minotaur has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). Minotaur was fine-tuned from the base model LLaMA-13B, please refer to its model card's Limitations Section for relevant information. (included below)

Benchmarks

hf-causal-experimental (pretrained=openaccess-ai-collective/minotaur-13b-fixed), limit: None, provide_description: False, num_fewshot: 0, batch_size: None

Task Version Metric Value Stderr
arc_challenge 0 acc 0.4778 _ 0.0146
acc_norm 0.4932 _ 0.0146
arc_easy 0 acc 0.7786 _ 0.0085
acc_norm 0.7487 _ 0.0089
boolq 1 acc 0.8141 _ 0.0068
hellaswag 0 acc 0.6072 _ 0.0049
acc_norm 0.7929 _ 0.0040
openbookqa 0 acc 0.3420 _ 0.0212
acc_norm 0.4580 _ 0.0223
piqa 0 acc 0.8025 _ 0.0093
acc_norm 0.8107 _ 0.0091
winogrande 0 acc 0.7285 _ 0.0125

Examples - results may vary based on temperature (0.7 for this) and other settings 

The following is a chat between a USER and a friendly and helpful ASSISTANT.
USER: Solve for x: 5x = 3x + 10
ASSISTANT:A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
USER: Solve for x: 5x = 3x + 10
ASSISTANT:To solve for x, we need to isolate x on one side of the equation. We can do this by following these steps:

1. Subtract 3x from both sides of the equation:
5x - 3x = 3x + 10 - 3x
2x = 10

2. Divide both sides of the equation by 2:
2x/2 = 10/2
x = 5

The following is a chat between a USER and a friendly and helpful ASSISTANT.
USER: You have 3 apples. You eat 2 pears. How many apples do you have left?
ASSISTANT:You still have 3 apples. Eating pears does not affect the number of apples you have.

The following is a chat between a USER and a friendly and helpful ASSISTANT.
USER: List three words that start with "ex". What is 33 + 77?
ASSISTANT:Three words that start with "ex" are "express", "exact", and "excite". 33 + 77 = 110.

The following is a chat between a USER and a friendly and helpful ASSISTANT.
USER: Write a haiku about dinosaurs.
ASSISTANT:Titanic creatures roam,
Thunderous footsteps echo,
Extinct but not forgotten.

meh, 6/7/7 rather than 5/7/5

A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.                                                                 
USER: Create an original short story in the style of J.K Rowling about the Weesley family going on a vacation in Australia whith Harry Potter and Hermione Grainger tagging along.                                             
ASSISTANT:Once upon a time, there was a magical family named the Weesleys. They lived in a cozy little cottage at the edge of Hogsmeade village, where they ran a charming bed and breakfast called "The Flying Ford Anglia." A
s any other magical family, they enjoyed adventures that brought them close to nature, so they decided to go on a trip to Australia. They invited their dear friends Harry Potter and Hermione Grainger to join them on this ex
citing journey.                                                                                                                                                                                                                

The Weesleys had been planning for months and had everything ready for their trip. Their children, Freddie and Roxanne were thrilled to visit the land down under, and their parents, George and Angelina, could not wait to ex
plore the beautiful country with their friends. They would be leaving soon, but before departing, there was one small problem - the luggage.

"We can't possibly take all these trunks!" exclaimed Freddie as he stared at the mountain of bags stacked up in front of him.

His father looked at him seriously. "You see, son," he began, "our luggage is crucial because we have to pack all our magical essentials like wand holsters, extra wand chargers, spell books, potions ingredients, and much mo
re."

Roxanne interrupted, "But daddy, we don't even use magic in everyday life! And what if it rains? We'll look weird carrying umbrellas around!"

Her mother joined in. "My dear, you know how unpredictable the weather can be. We must always be prepared for unexpected circumstances. Don't forget that even Muggles carry umbrellas."

After hours of debating, they finally managed to narrow down their luggage list and fit all the necessary supplies into several large trunks. The day had come; they were ready to leave for their grand adventure!

As the Weesleys boarded the Portkey that would transport them across the world, their wands began to glow softly, indicating that they had enough energy to make the journey. The Portkey dropped them off in Sydney, right in 
front of the magnificent Opera House.

They spent the first few days exploring the city, marveling at the iconic architecture and tasting local cuisine. Then, as planned, they headed north to visit the Great Barrier Reef, one of the most famous natural wonders o
f the world.

Harry and Hermione joined them during this leg of the trip, which made it even more enjoyable. Harry regaled them with tales of his own travels while Hermione shared her extensive knowledge of plants, animals, and the envir
onment.

Soon, they arrived at a quaint town nestled among vibrant green hills and surrounded by vast cattle farms. It was here that they would learn about Aboriginal culture and see some truly unique sights.

One morning, after enjoying a hearty breakfast, they set out to explore the local area. They visited a nearby art gallery that showcased amazing Indigenous works of art, including traditional paintings, sculptures, and text
iles. Afterward, they attended a didgeridoo concert given by a talented young musician who captivated everyone with his soulful tunes.

The following day, they embarked on a bushwalk through the rainforest trails. The air was cool and fresh, and the towering trees seemed to reach for the sky. Hermione took great pleasure in identifying various species of pl
ants and explaining their medicinal properties.

As they walked deeper into the forest, they heard faint chattering noises coming from high above. To their surprise, they spotted a group of small, furry creatures perched on a tree branch. They turned out to be native Aust
ralian possums, which delighted the children, especially Freddie, who could communicate with them using sign language.

Later that afternoon, they visited Uluru, also known as Ayers Rock, a massive sandstone monolith located in the heart of the Outback. The sight of its magnificent red hues against the blue sky left them all speechless. They
 spent the rest of the day exploring the rock formation, taking in the breathtaking views and learning about its significance to the Anangu people.

Their last destination was Queensland, home to the world-famous Great Barrier Reef. They spent two days snorkeling, diving, and swimming among the colorful coral reefs, watching schools of fish, sea turtles, and dolphins sw
im past them.

As the sun began to set over the crystal-clear waters, Harry spoke up. "I think it's time we return to reality, don't you agree?" he said, looking at his wife. "This trip has been fantastic, but we can't stay forever."

Everyone nodded in agreement as they prepared themselves for their final journey back to Sydney. When they got there, they gathered on the balcony of their hotel room, reminiscing about the incredible memories they had crea
ted together.

"Thank you for inviting us along on your adventure, Weesleys," said Harry. "It was an honor and a privilege to share this experience with such kind and generous friends. I hope we can do it again sometime."

With tears in their eyes and heavy hearts, they bid each other farewell, promising to keep in touch and meet again soon. And so, their epic journey came to an end. But the memories would remain with them forever, reminding 
them of the power of friendship, the beauty of nature, and the importance of discovering new worlds.
Downloads last month
42
Safetensors
Model size
2.03B params
Tensor type
F32
·
I32
·
FP16
·
Inference Examples
Text Generation
Inference API (serverless) has been turned off for this model.

Model tree for TheBloke/minotaur-13B-fixed-GPTQ

Base model

openaccess-ai-collective/minotaur-13b-fixed
Quantized
(3)
this model

Datasets used to train TheBloke/minotaur-13B-fixed-GPTQ