Hugging Face's logo

TheBloke
/
Luna-AI-Llama2-Uncensored-GPTQ

Text Generation
Transformers
Safetensors
llama
text-generation-inference
4-bit precision
gptq
Model card Files Community
5
Luna-AI-Llama2-Uncensored-GPTQ / README.md
TheBloke's picture
TheBloke
Update for Transformers GPTQ support
a0a8532
preview code
|
raw
history blame
13.1 kB
metadata
inference: false
license: other
model_type: llama
TheBlokeAI

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

Tap-M's Luna AI Llama2 Uncensored GPTQ

These files are GPTQ model files for Tap-M's Luna AI Llama2 Uncensored.

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.

Many thanks to William Beauchamp from Chai for providing the hardware used to make and upload these files!

Repositories available

Prompt template: User-Assistant 

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.

Branch Bits Group Size Act Order (desc_act) File Size ExLlama Compatible? Made With Description
main 4 128 False 3.90 GB True AutoGPTQ Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options.
gptq-4bit-32g-actorder_True 4 32 True 4.28 GB True AutoGPTQ 4-bit, with Act Order and group size. 32g gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed.
gptq-4bit-64g-actorder_True 4 64 True 4.02 GB True AutoGPTQ 4-bit, with Act Order and group size. 64g uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed.
gptq-4bit-128g-actorder_True 4 128 True 3.90 GB True AutoGPTQ 4-bit, with Act Order and group size. 128g uses even less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed.
gptq-8bit--1g-actorder_True 8 None True 7.01 GB False AutoGPTQ 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed.
gptq-8bit-128g-actorder_False 8 128 False 7.16 GB False AutoGPTQ 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed.
gptq-8bit-128g-actorder_True 8 128 True 7.16 GB False AutoGPTQ 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed.
gptq-8bit-64g-actorder_True 8 64 True 7.31 GB False AutoGPTQ 8-bit, with group size 64g and Act Order for maximum inference quality. Poor AutoGPTQ CUDA speed.

How to download from branches

  • In text-generation-webui, you can add :branch to the end of the download name, eg TheBloke/Luna-AI-Llama2-Uncensored-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/Luna-AI-Llama2-Uncensored-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.

  1. Click the Model tab.
  2. Under Download custom model or LoRA, enter TheBloke/Luna-AI-Llama2-Uncensored-GPTQ.
  • To download from a specific branch, enter for example TheBloke/Luna-AI-Llama2-Uncensored-GPTQ:gptq-4bit-32g-actorder_True
  • 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: Luna-AI-Llama2-Uncensored-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 set 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

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/Luna-AI-Llama2-Uncensored-GPTQ"
model_basename = "model"

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'''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.

Special thanks to: Aemon Algiz.

Patreon special mentions: Sam, theTransient, Jonathan Leane, Steven Wood, webtim, Johann-Peter Hartmann, Geoffrey Montalvo, Gabriel Tamborski, Willem Michiel, John Villwock, Derek Yates, Mesiah Bishop, Eugene Pentland, Pieter, Chadd, Stephen Murray, Daniel P. Andersen, terasurfer, Brandon Frisco, Thomas Belote, Sid, Nathan LeClaire, Magnesian, Alps Aficionado, Stanislav Ovsiannikov, Alex, Joseph William Delisle, Nikolai Manek, Michael Davis, Junyu Yang, K, J, Spencer Kim, Stefan Sabev, Olusegun Samson, transmissions 11, Michael Levine, Cory Kujawski, Rainer Wilmers, zynix, Kalila, Luke @flexchar, Ajan Kanaga, Mandus, vamX, Ai Maven, Mano Prime, Matthew Berman, subjectnull, Vitor Caleffi, Clay Pascal, biorpg, alfie_i, 阿明, Jeffrey Morgan, ya boyyy, Raymond Fosdick, knownsqashed, Olakabola, Leonard Tan, ReadyPlayerEmma, Enrico Ros, Dave, Talal Aujan, Illia Dulskyi, Sean Connelly, senxiiz, Artur Olbinski, Elle, Raven Klaugh, Fen Risland, Deep Realms, Imad Khwaja, Fred von Graf, Will Dee, usrbinkat, SuperWojo, Alexandros Triantafyllidis, Swaroop Kallakuri, Dan Guido, John Detwiler, Pedro Madruga, Iucharbius, Viktor Bowallius, Asp the Wyvern, Edmond Seymore, Trenton Dambrowitz, Space Cruiser, Spiking Neurons AB, Pyrater, LangChain4j, Tony Hughes, Kacper Wikieł, Rishabh Srivastava, David Ziegler, Luke Pendergrass, Andrey, Gabriel Puliatti, Lone Striker, Sebastain Graf, Pierre Kircher, Randy H, NimbleBox.ai, Vadim, danny, Deo Leter

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: Tap-M's Luna AI Llama2 Uncensored

Model Description

“Luna AI Llama2 Uncensored” is a Llama2 based Chat model
fine-tuned on over 40,000 long form chat discussions
This model was fine-tuned by Tap, the creator of Luna AI.
The result is an enhanced Llama2 7b model that rivals ChatGPT in performance
across a variety of tasks.

This model stands out for its long responses, low hallucination rate, and absence of censorship mechanisms.

Model Training

The fine-tuning process was performed on an 8x a100 80GB machine.
The model was trained almost entirely on synthetic outputs.
This includes data from diverse sources which we included to create our custom dataset, it includes multiple rounds of chats between Human & AI.

Prompt Format

The model follows the Vicuna 1.1/ OpenChat format:

USER: I have difficulties in making friends, and I really need someone to talk to. Would you be my friend?

ASSISTANT: Of course! Friends are always here for each other. What do you like to do?

Future Plans

The model is currently being uploaded in FP16 format,
and there are plans to convert the model to GGML and GPTQ 4bit quantizations.

Benchmark Results

Task Version Metric Value Stderr
arc_challenge 0 acc_norm 0.5512 0.0146
hellaswag 0
mmlu 0
truthfulqa_mc 1 mc2 0.4716 0.0155
Average - - 0.5114 0.0150

Ethical considerations

The data used to train the model is collected from various sources, mostly from the Web.
As such, it contains offensive, harmful and biased content.
We thus expect the model to exhibit such biases from the training data.

Human life

The model is not intended to inform decisions about matters central to human life,
and should not be used in such a way.

Risks and harms

Risks and harms of large language models include the generation of harmful, offensive or biased content.
These models are often prone to generating incorrect information, sometimes referred to as hallucinations.
We do not expect our model to be an exception in this regard.