Chat & support: my new Discord server

Want to contribute? TheBloke's Patreon page

OpenAccess AI Collective's Hippogriff 30B Chat GPTQ

These files are 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.

These models were quantised using hardware kindly provided by Latitude.sh .

Repositories available

• GPTQ models for GPU inference, with multiple quantisation parameter options.
• 2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference
• Unquantised fp16 model in pytorch format, for GPU inference and for further conversions

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

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.

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:gptq-4bit-32g-actorder_True
• With Git, you can clone a branch with:

git clone --branch gptq-4bit-32g-actorder_True 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 know how to make a manual install.

• To download from a specific branch, enter for example TheBloke/hippogriff-30b-chat-GPTQ:gptq-4bit-32g-actorder_True
• see Provided Files above for the list of branches for each option.

• Note that you do not need to set GPTQ parameters any more. These are set automatically from the file quantize_config.json .

How to use this GPTQ model from Python code

First make sure you have AutoGPTQ installed:

GITHUB_ACTIONS=true pip install auto-gptq

Then try the following example code:

from transformers import AutoTokenizer, pipeline, logging
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig

model_name_or_path = "TheBloke/hippogriff-30b-chat-GPTQ"
model_basename = "hippogriff-30b-GPTQ-4bit--1g.act.order"

use_triton = False

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)

model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
        model_basename=model_basename
        use_safetensors=True,
        trust_remote_code=False,
        device="cuda:0",
        use_triton=use_triton,
        quantize_config=None)

"""
To download from a specific branch, use the revision parameter, as in this example:

model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
        revision="gptq-4bit-32g-actorder_True",
        model_basename=model_basename,
        use_safetensors=True,
        trust_remote_code=False,
        device="cuda:0",
        quantize_config=None)
"""

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, max_new_tokens=512)
print(tokenizer.decode(output[0]))

# Inference can also be done using transformers' pipeline

# Prevent printing spurious transformers error when using pipeline with AutoGPTQ
logging.set_verbosity(logging.CRITICAL)

print("*** Pipeline:")
pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    max_new_tokens=512,
    temperature=0.7,
    top_p=0.95,
    repetition_penalty=1.15
)

print(pipe(prompt_template)[0]['generated_text'])

Compatibility

The files provided will work with AutoGPTQ (CUDA and Triton modes), GPTQ-for-LLaMa (only CUDA has been tested), and Occ4m's GPTQ-for-LLaMa fork.

ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.

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!

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 : Luke from CarbonQuill, Aemon Algiz.

Patreon special mentions : Space Cruiser, Nikolai Manek, Sam, Chris McCloskey, Rishabh Srivastava, Kalila, Spiking Neurons AB, Khalefa Al-Ahmad, WelcomeToTheClub, Chadd, Lone Striker, Viktor Bowallius, Edmond Seymore, Ai Maven, Chris Smitley, Dave, Alexandros Triantafyllidis, Luke @flexchar, Elle, ya boyyy, Talal Aujan, Alex , Jonathan Leane, Deep Realms, Randy H, subjectnull, Preetika Verma, Joseph William Delisle, Michael Levine, chris gileta, K, Oscar Rangel, LangChain4j, Trenton Dambrowitz, Eugene Pentland, Johann-Peter Hartmann, Femi Adebogun, Illia Dulskyi, senxiiz, Daniel P. Andersen, Sean Connelly, Artur Olbinski, RoA, Mano Prime, Derek Yates, Raven Klaugh, David Flickinger, Willem Michiel, Pieter, Willian Hasse, vamX, Luke Pendergrass, webtim, Ghost , Rainer Wilmers, Nathan LeClaire, Will Dee, Cory Kujawski, John Detwiler, Fred von Graf, biorpg, Iucharbius , Imad Khwaja, Pierre Kircher, terasurfer , Asp the Wyvern, John Villwock, theTransient, zynix , Gabriel Tamborski, Fen Risland, Gabriel Puliatti, Matthew Berman, Pyrater, SuperWojo, Stephen Murray, Karl Bernard, Ajan Kanaga, Greatston Gnanesh, Junyu Yang.

Thank you to all my generous patrons and donaters!

Original model card: OpenAccess AI Collective's Hippogriff 30B Chat

Hippogriff 30B Chat

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

• OpenAssistant/oasst1 - cleaned dataset, similar to Guanaco
• synthetic jokes generation and explanation derived from reddit jokes dataset
• synthetic prose generation and rewriting self-chat
• Q&A based on provided context
• self instruct augmented logic_inference_oa
• de-duped pygmalion dataset, filtered down to RP data, cleaned, english only, 25%
• riddle_sense - instruct augmented
• hellaswag, updated for detailed explanations w 30K+ rows
• gsm8k - instruct augmented
• ewof/code-alpaca-instruct-unfiltered synthetic self chat dataset derived from about 1000 rows
• subset of QingyiSi/Alpaca-CoT for roleplay and CoT
• GPTeacher-General-Instruct
• ARC-Easy & ARC-Challenge - instruct augmented for detailed responses, derived from the train split
• hellaswag - 5K row subset of instruct augmented for concise responses, derived from the train split
• metaeval/ScienceQA_text_only - instruct for concise responses
• openai/summarize_from_feedback - instruct augmented tl;dr summarization

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