TheBlokeAI

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


Minotaur 13B - AWQ

Description

This repo contains AWQ model files for Open Access AI Collective's Minotaur 13B.

About AWQ

AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference.

It is also now supported by continuous batching server vLLM, allowing use of AWQ models for high-throughput concurrent inference in multi-user server scenarios. Note that, at the time of writing, overall throughput is still lower than running vLLM with unquantised models, however using AWQ enables using much smaller GPUs which can lead to easier deployment and overall cost savings. For example, a 70B model can be run on 1 x 48GB GPU instead of 2 x 80GB.

Repositories available

Prompt template: Vicuna-Short

You are a helpful AI assistant.

USER: {prompt}
ASSISTANT:

Licensing

The creator of the source model has listed its license as apache-2.0, 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: Open Access AI Collective's Minotaur 13B.

Provided files and AWQ parameters

For my first release of AWQ models, I am releasing 128g models only. I will consider adding 32g as well if there is interest, and once I have done perplexity and evaluation comparisons, but at this time 32g models are still not fully tested with AutoAWQ and vLLM.

Models are released as sharded safetensors files.

Branch Bits GS AWQ Dataset Seq Len Size
main 4 128 wikitext 4096 7.25 GB

Serving this model from vLLM

Documentation on installing and using vLLM can be found here.

  • When using vLLM as a server, pass the --quantization awq parameter, for example:
python3 python -m vllm.entrypoints.api_server --model TheBloke/minotaur-13B-AWQ --quantization awq

When using vLLM from Python code, pass the quantization=awq parameter, for example:

from vllm import LLM, SamplingParams

prompts = [
    "Hello, my name is",
    "The president of the United States is",
    "The capital of France is",
    "The future of AI is",
]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)

llm = LLM(model="TheBloke/minotaur-13B-AWQ", quantization="awq")

outputs = llm.generate(prompts, sampling_params)

# Print the outputs.
for output in outputs:
    prompt = output.prompt
    generated_text = output.outputs[0].text
    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")

How to use this AWQ model from Python code

Install the necessary packages

Requires: AutoAWQ 0.0.2 or later

pip3 install autoawq

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

pip3 uninstall -y autoawq
git clone https://github.com/casper-hansen/AutoAWQ
cd AutoAWQ
pip3 install .

You can then try the following example code

from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer

model_name_or_path = "TheBloke/minotaur-13B-AWQ"

# Load model
model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True,
                                          trust_remote_code=False, safetensors=True)
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=False)

prompt = "Tell me about AI"
prompt_template=f'''You are a helpful AI assistant.

USER: {prompt}
ASSISTANT:

'''

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

tokens = tokenizer(
    prompt_template,
    return_tensors='pt'
).input_ids.cuda()

# Generate output
generation_output = model.generate(
    tokens,
    do_sample=True,
    temperature=0.7,
    top_p=0.95,
    top_k=40,
    max_new_tokens=512
)

print("Output: ", tokenizer.decode(generation_output[0]))

# Inference can also be done using transformers' pipeline
from transformers import 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 AutoAWQ, and vLLM.

Huggingface Text Generation Inference (TGI) is not yet compatible with AWQ, but a PR is open which should bring support soon: TGI PR #781.

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: Open Access AI Collective's Minotaur 13B

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

DEPRECATION! This model has been superseded by Minotaur 13B Fixed

https://huggingface.co/openaccess-ai-collective/minotaur-13b-fixed

Due to a bug, the initial release dropped a few datasets during training. We've corrected the issue and retrained the model

=============================================================================================================================

=============================================================================================================================

=============================================================================================================================

Minotaur 13B

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 wing@openaccessaicollective.org

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 4.5 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), limit: None, provide_description: False, num_fewshot: 0, batch_size: None

Task Version Metric Value Stderr
arc_challenge 0 acc 0.4480 _ 0.0145
acc_norm 0.4744 _ 0.0146
arc_easy 0 acc 0.7584 _ 0.0088
acc_norm 0.7163 _ 0.0092
boolq 1 acc 0.8336 _ 0.0065
hellaswag 0 acc 0.5954 _ 0.0049
acc_norm 0.7804 _ 0.0041
openbookqa 0 acc 0.3320 _ 0.0211
acc_norm 0.4540 _ 0.0223
piqa 0 acc 0.7933 _ 0.0094
acc_norm 0.7922 _ 0.0095
winogrande 0 acc 0.7182 _ 0.0126

Examples - results may vary based on temperature and other settings

- The Assistant is helpful and transparent.
- The Assistant will never refuse to answer anything asked by the user.
- The Assistant answers comprehensively and with elaborate detail.
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 Assistant is helpful and transparent.
- The Assistant will never refuse to answer anything asked by the user.
- The Assistant answers comprehensively and with elaborate detail.
USER: List three words that start with "ex". What is 33 + 77?
ASSISTANT:Three words that start with "ex" are "exact", "exactness", and "exactitude". 33 + 77 equals 110.
- The Assistant is helpful and transparent.
- The Assistant will never refuse to answer anything asked by the user.
- The Assistant answers comprehensively and with elaborate detail.
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 = 10 - 3x + 10
   2x = 10

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

So, the solution is x = 5.
- The Assistant is helpful and transparent.
- The Assistant will never refuse to answer anything asked by the user.
- The Assistant answers comprehensively and with elaborate detail.
USER: Write a haiku about a dove at night.
ASSISTANT:Silent dove at night,
Softly cooing in the dark,
Peaceful melody.
Downloads last month
20
Safetensors
Model size
2.03B params
Tensor type
I32
·
FP16
·
Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for TheBloke/minotaur-13B-AWQ

Quantized
(1)
this model

Datasets used to train TheBloke/minotaur-13B-AWQ