Hugging Face's logo

TheBloke
/
hippogriff-30b-chat-GPTQ

Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
4-bit precision
gptq
Model card Files Community
hippogriff-30b-chat-GPTQ / README.md
TheBloke's picture
TheBloke
Update base_model formatting
16ef2af
preview code
|
raw
history blame contribute delete
22.9 kB
metadata
language:
  - en
license: other
library_name: transformers
datasets:
  - QingyiSi/Alpaca-CoT
  - teknium/GPT4-LLM-Cleaned
  - teknium/GPTeacher-General-Instruct
  - metaeval/ScienceQA_text_only
  - hellaswag
  - openai/summarize_from_feedback
  - riddle_sense
  - gsm8k
  - OpenAssistant/oasst1
model_name: Hippogriff 30B Chat
base_model: openaccess-ai-collective/hippogriff-30b-chat
inference: false
model_creator: Open Access AI Collective
model_type: llama
pipeline_tag: text-generation
prompt_template: >
  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:
quantized_by: TheBloke
TheBlokeAI

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

Hippogriff 30B Chat - GPTQ

Description

This repo contains GPTQ model files for OpenAccess AI Collective's Hippogriff 30B Chat.

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 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 :branch to the end of the download name, eg TheBloke/hippogriff-30b-chat-GPTQ:main
  • With Git, you can clone a branch with:
git clone --single-branch --branch main https://huggingface.co/TheBloke/hippogriff-30b-chat-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/hippogriff-30b-chat-GPTQ.
  • To download from a specific branch, enter for example TheBloke/hippogriff-30b-chat-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: hippogriff-30b-chat-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/hippogriff-30b-chat-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=False,
                                             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 Hippogriff 30B Chat

Hippogriff 30B Chat

Built with Axolotl

Hippogriff 30B Chat is an experiment that builds on Manticore with new datasets, while removing a few more instruction and chat datasets. It also includes a de-duped subset of the Pygmalion dataset. It also removes all Alpaca style prompts using ### in favor of chat only style prompts using USER:,ASSISTANT: as well as pygmalion/metharme prompting using <|system|>, <|user|> and <|model|> tokens.

Questions, comments, feedback, looking to donate, or want to help? Reach out on our Discord or email wing@openaccessaicollective.org

Training Datasets

Hippogriff 30B Chat is a Llama 30B model fine-tuned on the following datasets

Hippogriff differs from Manticore as it does not use the WizardLM, WizardVicuna, Alpaca, or ShareGPT datasets.

Initial thoughts

Hippogriff follows instructions pretty well. It still struggles with anything that has to do with math. Prose is much better than manticore. Handles in-context QA much better.

Shoutouts

Special thanks to Nanobit for helping with Axolotl, TheBloke for quantizing these models are more accessible to all, 0x000011b for the RP dataset, and the support from everyone in our AI Discord community.

Demo

A Spaces demo is not provided for this release due to 30B models currently not fitting in VRAM.

Build

Hippogriff was built with Axolotl on 8xA100 80GB

  • 1.5 epochs taking approximately 12 hours. No further epochs will be released.

Bias, Risks, and Limitations

Hippogriff 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). Hippogriff was fine-tuned from the base model LlaMa 30B, please refer to its model card's Limitations Section for relevant information.

The core functionality of Llama is taking a string of text and predicting the next token. While language models are widely used for tasks other than this, there are a lot of unknowns with this work. When prompting Hippogriff it is important to remember that the statistically most likely next token is often not the token that produces the most "accurate" text. Never depend upon Hippogriff to produce factually accurate output.

Llama was trained on the Pile, a dataset known to contain profanity, lewd, and otherwise abrasive language. Depending upon use case Hippogriff may produce socially unacceptable text. See Sections 5 and 6 of the Pile paper for a more detailed analysis of the biases in the Pile.

As with all language models, it is hard to predict in advance how Hippogriff will respond to particular prompts and offensive content may occur without warning. We recommend having a human curate or filter the outputs before releasing them, both to censor undesirable content and to improve the quality of the results.

Examples

TBD

USER: write an original short story of at least 300 words in the style of Zora Neale Hurston. Incorporate the following literary devices: Euphemism and Foreshadowing.
ASSISTANT: Once upon a time, there was a black girl named Rose, whose skin shined like a pearl beneath the hot sun. She lived with her mama and daddy on their farm, where they grew crops to feed the family and neighbors. On this particular day, Rose felt a tinge of excitement as she watched her parents work diligently in their fields. 'It's almost harvest season!' she thought, imagining the delicious meals that awaited them. But, soon after, it became apparent that something sinister lurked amidst the rows of fresh produce. 

As her father hoed around a vine-covered cucumber plant, he unearthed a peculiar rock. It was the size of an acorn but had a strange shape, unlike anything he or his wife had ever seen. "What have we here?" He said, turning to his wife with curiosity and excitement. She examined the rock for herself and declared, "Why, it looks like a piece of coal!" But as both mother and daughter looked closer, it seemed to be far more than a mere piece of coal. A sense of unease crept up Rose's spine when she noticed that the rock resembled the dark face of a baby in the womb. As Rose tried to suppress a scream, her mother gasped, "Sweet Jesus! Let's bury this thing before anyone sees!" And so, they quickly hid the stone back underground, hoping that nobody would ever discover their secret.

USER: tell me 5 words that start with "ex" and then the sum of 33 and 77
ASSISTANT: Excite, exotic, exhibit, excitable, excessive

USER: sally (a girl) has 3 brothers. Each brother has 2 sisters. how many sisters does sally have?
ASSISTANT: Sally has 3 brothers, and each brother has 2 sisters. To find out how many sisters Sally has in total, we need to multiply the number of bro
thers by the number of sisters per brother, then add 1 to account for Sally herself. So, 3 * 2 + 1 = 6 sisters in total