Chat & support: TheBloke's Discord server

Want to contribute? TheBloke's Patreon page

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

Manticore 13B - GPTQ

Model creator: Open Access AI Collective
Original model: Manticore 13B

Description

This repo contains GPTQ model files for Open Access AI Collective's Manticore 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/Manticore-13B-GPTQ:main
With Git, you can clone a branch with:

git clone --single-branch --branch main https://huggingface.co/TheBloke/Manticore-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.

Click the Model tab.
Under Download custom model or LoRA, enter TheBloke/Manticore-13B-GPTQ.

To download from a specific branch, enter for example TheBloke/Manticore-13B-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: Manticore-13B-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/Manticore-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.

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: Open Access AI Collective's Manticore 13B

Manticore 13B - (previously Wizard Mega)

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

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

Manticore 13B is a Llama 13B model fine-tuned on the following datasets:

ShareGPT - based on a cleaned and de-suped subset
WizardLM
Wizard-Vicuna
subset of QingyiSi/Alpaca-CoT for roleplay and CoT
GPT4-LLM-Cleaned
GPTeacher-General-Instruct
ARC-Easy & ARC-Challenge - instruct augmented for detailed responses
mmlu: instruct augmented for detailed responses subset including
- abstract_algebra
- conceptual_physics
- formal_logic
- high_school_physics
- logical_fallacies
hellaswag - 5K row subset of instruct augmented for concise responses
metaeval/ScienceQA_text_only - instruct for concise responses
openai/summarize_from_feedback - instruct augmented tl;dr summarization

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.

https://huggingface.co/spaces/openaccess-ai-collective/manticore-ggml

Release Notes

https://wandb.ai/wing-lian/manticore-13b/runs/nq3u3uoh/workspace

Build

Manticore was built with Axolotl on 8xA100 80GB

Preview Release: 3 epochs taking approximately 24 hours.
The configuration to duplicate this build is provided in this repo's /config folder.

Bias, Risks, and Limitations

Manticore 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). Manticore 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:
Here’s an example of how you can use memoization to efficiently calculate the first n numbers of the Fibonacci sequence in Python:
```
def fib(n):
 # Memoize the last calculated Fibonacci number for each index
 cache = {}
 
 def fib_memoized(n):
 if n not in cache:
 cache[n] = [0, 1]
 else:
 return cache[n][-1], cache[n][-2]
 
 # Recursive helper function to calculate the Fibonacci sequence up to a given index
 def fib_helper(n):
 if n == 0 or n == 1:
 return 0, 1
 else:
 return fib_helper(n - 1) + fib_helper(n - 2)
 
# Calculate the first n numbers of the Fibonacci sequence using memoization
 def fib_memoized_seq(n):
 if n == 0 or n == 1:
 return 0, 1
 else:
 result = fib_helper(n - 1) + fib_helper(n - 2)
 cache[n] = [result]
 return result, cache[n][-1], cache[n][-2]
 
 # Example usage
 for i in range(len(fib_memoized_seq(3))):
 print(fib_memoized_seq(3)[i])
```

In this implementation, we use a cache dictionary to memoize the last calculated Fibonacci number for each index. We define two helper functions: fib_helper, which recursively calculates the Fibonacci sequence up to a given index, and fib_memoized, which uses memoization to efficiently calculate the first n numbers of the Fibonacci sequence. Finally, we define the fib_memoized_seq function, which is our main function for calculating the first n numbers of the Fibonacci sequence using memoization.

USER: Finish the joke, a mechanic and a car salesman walk into a bar...  
ASSISTANT: … and when they get up to leave, they realize that they’ve left their keys in their cars. The mechanic says “I know how to fix this” and opens his toolbox to grab something. Then he stops and looks at the salesman. He says “You drive a Toyota, right?” The salesman nods. The mechanic then takes out a tiny screwdriver from his toolbox and starts working on the lock of the car door. The salesman is amazed and asks how he knew that. The mechanic replies “I can tell by the way you parked your car.”

USER: Describe how a tsunami would affect the residents of Denver Colorado
ASSISTANT: The impact of a tsunami in Denver, Colorado would likely be minimal. As there are no coastal areas or bodies of water nearby, a tsunami generated from an earthquake or volcanic activity elsewhere in the world would have little effect on the city and its residents. Even if a large tsunami were to hit the coastline of California or Mexico, the distance between Denver and these locations means that any impacts on the city itself would be minimal.

USER: If you could do one thing right now, what would it be?
ASSISTANT: I’d hug my loved ones a little tighter today and tell them how much they mean to me. 
USER: And who are your loved ones?
ASSISTANT: My closest friends and family members.
USER: What are their names?
ASSISTANT: My two best friends are named Emily and Jessica, my mom is Mary, and my dad is David. Answering the question with a bit more information about who they are or what they mean to me would help provide a more personalized response.

TheBloke
/

Manticore-13B-GPTQ