Downloads · 30 days
96
8% of all-time downloads
TheBloke/13B-BlueMethod-GPTQ
13B-BlueMethod-GPTQ is a text generation model from TheBloke. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
<div style="width: auto; margin-left: auto; margin-right: auto" <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;" </div <div style="displa…
Downloads · 30 days
96
8% of all-time downloads
All-time downloads
1.2K
Public
Parameters
13B
169 GB on disk
Likes
6
Public
Click a slice to open those files.
.safetensors7.3 GB · 100%
How the weights are stored.
I3212.7B · 97%
From the Hugging Face model README
This repo contains GPTQ model files for CalderaAI's 13B BlueMethod.
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.
<!-- description end --> <!-- repositories-available start -->Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
<!-- prompt-template end -->
<!-- README_GPTQ.md-provided-files start -->
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.
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.| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
|---|---|---|---|---|---|---|---|---|---|
| main | 4 | 128 | No | 0.01 | wikitext | 2048 | 7.26 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-128g-actorder_True | 8 | 128 | Yes | 0.01 | wikitext | 2048 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
| gptq-8bit-64g-actorder_True | 8 | 64 | Yes | 0.01 | wikitext | 2048 | 13.95 GB | No | 8-bit, with group size 64g and Act Order for even higher inference quality. Poor AutoGPTQ CUDA speed. |
| 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. |
| 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. |
:branch to the end of the download name, eg TheBloke/13B-BlueMethod-GPTQ:maingit clone --single-branch --branch main https://huggingface.co/TheBloke/13B-BlueMethod-GPTQ
revision parameter; see below.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.
TheBloke/13B-BlueMethod-GPTQ.TheBloke/13B-BlueMethod-GPTQ:main13B-BlueMethod-GPTQquantize_config.json.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 .
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
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/13B-BlueMethod-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'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'''
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'])
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
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.
<!-- README_GPTQ.md-compatibility end --> <!-- footer start --> <!-- 200823 -->For further support, and discussions on these models and AI in general, join us at:
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.
<!-- footer end -->BlueMethod is a bit of a convoluted experiment in tiered merging. Furthering the experimental nature of the merge, the models combined were done so with a custom script that randomized the percent of each layer merged from one model to the next. This is a warmup for a larger project. [Tier One and Two Merges not released; internal naming convention]
Tier One Merges:
13B-Metharme+13B-Nous-Hermes=13B-Methermes
13B-Vicuna-cocktail+13B-Manticore=13B-Vicortia
13B-HyperMantis+13B-Alpacino=13B-PsychoMantis
Tier Two Merges:
13B-Methermes+13B-Vicortia=13B-Methphistopheles
13B-PsychoMantis+13B-BlueMoonRP=13B-BlueMantis
Tier Three Merge:
13B-Methphistopheles+13B-BlueMantis=13B-BlueMethod
Multiple instruct models and model composites were combined to make the final resulting model; This model is highly open to experimental prompting, both Alpaca and Vicuna instruct can be used. It can have interesting results.
13B-Metharme by PygmalionAI
https://www.huggingface.co/PygmalionAI/metharme-13b
13B-Nous-Hermes by NousResearch
https://www.huggingface.co/NousResearch/Nous-Hermes-13b
13B-Vicuna-cocktail by reeducator
https://www.huggingface.co/reeducator/vicuna-13b-cocktail
13B-Manticore by openaccess-ai-collective
https://www.huggingface.co/openaccess-ai-collective/manticore-13b
13B-HyperMantis and 13B-Alpacino by Digitous
https://huggingface.co/digitous/13B-HyperMantis https://huggingface.co/digitous/Alpacino13b
Also thanks to Meta for LLaMA.
Each model and LoRA was hand picked and considered for what it could contribute to this ensemble. Thanks to each and every one of you for your incredible work developing some of the best things to come out of this community.