Mythomax L2 13B AWQ

🚀 MythoMax L2 13B - AWQ

This repository provides AWQ model files for MythoMax L2 13B, offering efficient and fast low-bit weight quantization for inference.

🚀 Quick Start

This README offers comprehensive details about the MythoMax L2 13B - AWQ model, including its description, available repositories, prompt template, licensing, provided files, and usage instructions.

✨ Features

• AWQ Quantization: Utilizes the efficient, accurate, and fast AWQ low-bit weight quantization method, currently supporting 4-bit quantization. It offers faster Transformers-based inference compared to GPTQ.
• vLLM Support: Now supported by the continuous batching server vLLM, enabling high-throughput concurrent inference in multi - user server scenarios.
• Multiple Repositories: Available in multiple formats for different inference needs, including AWQ, GPTQ, and GGUF models, as well as the original unquantized fp16 model.
• Role - playing and Storywriting: Proficient at both roleplaying and storywriting, thanks to its unique merge of MythoLogic - L2 and Huginn.

📦 Installation

Installing Necessary Packages for Python Use

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 .

💻 Usage Examples

Serving the Model from vLLM

When using vLLM as a server, pass the --quantization awq parameter:

python3 python -m vllm.entrypoints.api_server --model TheBloke/MythoMax-L2-13B-AWQ --quantization awq

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

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/MythoMax-L2-13B-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}")

Using the AWQ Model from Python Code

from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer

model_name_or_path = "TheBloke/MythoMax-L2-13B-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'''Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

'''

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'])

📚 Documentation

Description

This repo contains AWQ model files for Gryphe's MythoMax L2 13B.

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

Prompt Template: Custom

{system_message}

### Instruction:
{prompt}
(For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.)

### Response:

Licensing

The creator of the source model has listed its license as other, 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: Gryphe's MythoMax L2 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.

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.

🔧 Technical Details

The model is a merge of MythoLogic - L2 and Huginn. Each layer of the model is composed of several tensors, which are responsible for specific functions. Using MythoLogic - L2's robust understanding as its input and Huginn's extensive writing capability as its output seems to have resulted in a model that excels at both. This type of merge is complex, as each of its 363 tensors had a unique ratio applied to it, and gradients were part of these ratios to further finetune its behaviour.

📄 License

The model is under the other license as specified by the source model creator. It is also subject to the Meta Llama 2 license terms due to its base on Llama 2. For more details on licensing, refer to the original model repository: Gryphe's MythoMax L2 13B.

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: 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.