TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)
30B Epsilon - GPTQ
- Model creator: Caldera AI
- Original model: 30B Epsilon
Description
This repo contains GPTQ model files for CalderaAI's 30B Epsilon.
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
- 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
- Caldera AI's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions
Prompt template: Alpaca
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
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 | None | Yes | 0.01 | wikitext | 2048 | 16.94 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
| gptq-4bit-32g-actorder_True | 4 | 32 | Yes | 0.01 | wikitext | 2048 | 19.44 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 | 18.18 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 | 17.55 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 | 32.99 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 | 33.73 GB | No | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
| gptq-3bit--1g-actorder_True | 3 | None | Yes | 0.01 | wikitext | 2048 | 12.92 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
| gptq-3bit-128g-actorder_False | 3 | 128 | No | 0.01 | wikitext | 2048 | 13.51 GB | No | 3-bit, with group size 128g but no act-order. Slightly higher VRAM requirements than 3-bit None. |
How to download from branches
- In text-generation-webui, you can add
:branchto the end of the download name, egTheBloke/30B-Epsilon-GPTQ:main - With Git, you can clone a branch with:
git clone --single-branch --branch main https://huggingface.co/TheBloke/30B-Epsilon-GPTQ
- In Python Transformers code, the branch is the
revisionparameter; 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.
- Click the Model tab.
- Under Download custom model or LoRA, enter
TheBloke/30B-Epsilon-GPTQ.
- To download from a specific branch, enter for example
TheBloke/30B-Epsilon-GPTQ:main - see Provided Files above for the list of branches for each option.
- Click Download.
- The model will start downloading. Once it's finished it will say "Done".
- In the top left, click the refresh icon next to Model.
- In the Model dropdown, choose the model you just downloaded:
30B-Epsilon-GPTQ - The model will automatically load, and is now ready for use!
- 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.
- 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/30B-Epsilon-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'])
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:
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.
Original model card: CalderaAI's 30B Epsilon
30B-Epsilon
Epsilon is an instruct based general purpose model assembled from hand picked models and LoRAs. There is no censorship and it follows instructions in the Alpaca format. This means you can create your own rules in the context memory of your inference system of choice [mainly KoboldAI or Text Generation Webui and chat UIs like SillyTavern and so on].
Composition:
This model is the result of an experimental use of LoRAs on language models and model merges. [] = applied as LoRA to a composite model | () = combined as composite models 30B-Epsilon = [SuperCOT[SuperHOT-prototype13b-8192[(wizardlmuncensored+((hippogriff+manticore)+(StoryV2))]
Alpaca's instruct format can be used to do many things, including control of the terms of behavior between a user and a response from an agent in chat. Below is an example of a command injected into memory.
### Instruction:
Make Narrator function as a text based adventure game that responds with verbose, detailed, and creative descriptions of what happens next after Player's response.
Make Player function as the player input for Narrator's text based adventure game, controlling a character named (insert character name here, their short bio, and
whatever quest or other information to keep consistent in the interaction).
### Response:
{an empty new line here}
All datasets from all models and LoRAs used were documented and reviewed as model candidates for merging. Model candidates were based on five core principles: creativity, logic, inference, instruction following, and longevity of trained responses. SuperHOT-prototype30b-8192 was used in this mix, not the 8K version; the prototype LoRA seems to have been removed [from HF] as of this writing. The GPT4Alpaca LoRA from Chansung was removed from this amalgam following a thorough review of where censorship and railroading the user came from in 33B-Lazarus. This is not a reflection of ChanSung's excellent work - it merely did not fit the purpose of this model.
Language Models and LoRAs Used Credits:
manticore-30b-chat-pyg-alpha [Epoch0.4] by openaccess-ai-collective
https://huggingface.co/openaccess-ai-collective/manticore-30b-chat-pyg-alpha
hippogriff-30b-chat by openaccess-ai-collective
https://huggingface.co/openaccess-ai-collective/hippogriff-30b-chat
WizardLM-33B-V1.0-Uncensored by ehartford
https://huggingface.co/ehartford/WizardLM-33B-V1.0-Uncensored
Storytelling-LLaMa-LoRA [30B, Version 2] by GamerUnTouch
https://huggingface.co/GamerUntouch/Storytelling-LLaMa-LoRAs
SuperCOT-LoRA [30B] by kaiokendev
https://huggingface.co/kaiokendev/SuperCOT-LoRA
SuperHOT-LoRA-prototype30b-8192 [30b, not 8K version, but a removed prototype] by kaiokendev
https://huggingface.co/kaiokendev/superhot-30b-8k-no-rlhf-test [Similar LoRA to one since removed that was used in making this model.]
Also thanks to Meta for LLaMA and to each and every one of you who developed these fine-tunes and LoRAs.
- Downloads last month
- 10