Hugging Face's logo

TheBloke
/
wizard-mega-13B-GPTQ

Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
4-bit precision
gptq
Model card Files Community
6
wizard-mega-13B-GPTQ / README.md
TheBloke's picture
TheBloke
Update base_model formatting
df7beb2
preview code
|
raw
history blame contribute delete
17.2 kB
metadata
language:
  - en
license: other
library_name: transformers
datasets:
  - anon8231489123/ShareGPT_Vicuna_unfiltered
  - ehartford/wizard_vicuna_70k_unfiltered
  - ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered
model_name: Wizard Mega 13B
base_model: openaccess-ai-collective/wizard-mega-13b
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)

Wizard Mega 13B - GPTQ

Description

This repo contains GPTQ model files for Open Access AI Collective's Wizard Mega 13B.

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 4 128 No 0.01 wikitext 2048 7.45 GB Yes 4-bit, without Act Order and group size 128g.

How to download from branches

  • In text-generation-webui, you can add :branch to the end of the download name, eg TheBloke/wizard-mega-13B-GPTQ:main
  • With Git, you can clone a branch with:
git clone --single-branch --branch main https://huggingface.co/TheBloke/wizard-mega-13B-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/wizard-mega-13B-GPTQ.
  • To download from a specific branch, enter for example TheBloke/wizard-mega-13B-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: wizard-mega-13B-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/wizard-mega-13B-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: Open Access AI Collective's Wizard Mega 13B

Wizard Mega 13B has been updated and is now Manticore 13B

Built with Axolotl 💵 Donate to OpenAccess AI Collective to help us keep building great tools and models!

Manticore is available at https://huggingface.co/openaccess-ai-collective/manticore-13b and fixes many issues with Wizard Mega and adds new datasets to the training.

Wizard Mega is a Llama 13B model fine-tuned on the ShareGPT, WizardLM, and Wizard-Vicuna datasets. These particular datasets have all been filtered to remove responses where the model responds with "As an AI language model...", etc or when the model refuses to respond.

Demo

Try out the model in HF Spaces. The demo uses a quantized GGML version of the model to quickly return predictions on smaller GPUs (and even CPUs). Quantized GGML may have some minimal loss of model quality.

Release (Epoch Two)

The Wizard Mega 13B SFT model is being released after two epochs as the eval loss increased during the 3rd (final planned epoch). Because of this, we have preliminarily decided to use the epoch 2 checkpoint as the final release candidate. https://wandb.ai/wing-lian/vicuna-13b/runs/5uebgm49

Build

Wizard Mega was built with Axolotl on 8xA100 80GB for 15 hours. The configuration to duplicate this build is provided in this repo's /config folder.

Bias, Risks, and Limitations

Wizard Mega 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). Wizard Mega was fine-tuned from the base model LlaMa 13B, please refer to its model card's Limitations Section for relevant information.

Examples 

### Instruction: write Python code that returns the first n numbers of the Fibonacci sequence using memoization.

### Assistant: 
```python
def fib(n):
    if n < 2:
        return n
    elif n in cache:
        return cache[n]
    else:
        a, b = 0, 1
        for i in range(2, n+1):
            cache[i] = a
            a, b = b, a + b
        return cache[n]
    
def first_n(n):
    fib_list = [fib(i) for i in range(n+1)]
    return fib_list[:n]
```
This function uses memoization to store the values of previous Fibonacci numbers in a cache. This way, if the same number is requested again, it can be returned immediately without recalculating it. 
The `first_n` function takes an integer `n` as input, and calculates the first n numbers of the Fibonacci sequence using memoization. It returns a list of those numbers.

### Instruction: Finish the joke, a mechanic and a car salesman walk into a bar...  

### Assistant:  ...and the bartender says "Hey guys, what can I get for you?" The mechanic replies, "I'll have a beer, but make it a quick one. I have to fix this guy's car before he finds out I
 fiddled with his brakes." The salesman quips, "And I'll have a martini, shaken not stirred. After all, I have to sell this guy a car that doesn't break down on him within the first year of ownership."