TheBloke/llemma_7b-GPTQ

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)

---

Llemma 7B - GPTQ

• Model creator: EleutherAI
• Original model: Llemma 7B

Description

This repo contains GPTQ model files for EleutherAI's Llemma 7B.

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

• AWQ model(s) for GPU inference.
• GPTQ models for GPU inference, with multiple quantisation parameter options.
• 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference
• EleutherAI's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

Prompt template: Unknown

{prompt}

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.

Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.

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 calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration 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	Yes	0.1	CamelAI Math	4096	3.90 GB	Yes	4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy.
gptq-4bit-32g-actorder_True	4	32	Yes	0.1	CamelAI Math	4096	4.28 GB	Yes	4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage.
gptq-8bit--1g-actorder_True	8	None	Yes	0.1	CamelAI Math	4096	7.01 GB	No	8-bit, with Act Order. No group size, to lower VRAM requirements.
gptq-8bit-128g-actorder_True	8	128	Yes	0.1	CamelAI Math	4096	7.16 GB	No	8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy.
gptq-8bit-32g-actorder_True	8	32	Yes	0.1	CamelAI Math	4096	7.62 GB	No	8-bit, with group size 32g and Act Order for maximum inference quality.
gptq-4bit-64g-actorder_True	4	64	Yes	0.1	CamelAI Math	4096	4.02 GB	Yes	4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy.

How to download, including from branches

In text-generation-webui

To download from the main branch, enter TheBloke/llemma_7b-GPTQ in the "Download model" box.

To download from another branch, add :branchname to the end of the download name, eg TheBloke/llemma_7b-GPTQ:gptq-4bit-32g-actorder_True

From the command line

I recommend using the huggingface-hub Python library:

pip3 install huggingface-hub

To download the main branch to a folder called llemma_7b-GPTQ:

mkdir llemma_7b-GPTQ
huggingface-cli download TheBloke/llemma_7b-GPTQ --local-dir llemma_7b-GPTQ --local-dir-use-symlinks False

To download from a different branch, add the --revision parameter:

mkdir llemma_7b-GPTQ
huggingface-cli download TheBloke/llemma_7b-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir llemma_7b-GPTQ --local-dir-use-symlinks False

More advanced huggingface-cli download usage

If you remove the --local-dir-use-symlinks False parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: ~/.cache/huggingface), and symlinks will be added to the specified --local-dir, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.

The cache location can be changed with the HF_HOME environment variable, and/or the --cache-dir parameter to huggingface-cli.

For more documentation on downloading with huggingface-cli, please see: HF -> Hub Python Library -> Download files -> Download from the CLI.

To accelerate downloads on fast connections (1Gbit/s or higher), install hf_transfer:

pip3 install hf_transfer

And set environment variable HF_HUB_ENABLE_HF_TRANSFER to 1:

mkdir llemma_7b-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/llemma_7b-GPTQ --local-dir llemma_7b-GPTQ --local-dir-use-symlinks False

Windows Command Line users: You can set the environment variable by running set HF_HUB_ENABLE_HF_TRANSFER=1 before the download command.

With git (not recommended)

To clone a specific branch with git, use a command like this:

git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/llemma_7b-GPTQ

Note that using Git with HF repos is strongly discouraged. It will be much slower than using huggingface-hub, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the .git folder as a blob.)

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/llemma_7b-GPTQ.

   • To download from a specific branch, enter for example TheBloke/llemma_7b-GPTQ:gptq-4bit-32g-actorder_True
   • see Provided Files above for the list of branches for each option.

3. Click Download.

4. The model will start downloading. Once it's finished it will say "Done".

5. In the top left, click the refresh icon next to Model.

6. In the Model dropdown, choose the model you just downloaded: llemma_7b-GPTQ

7. The model will automatically load, and is now ready for use!

8. 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.

9. Once you're ready, click the Text Generation tab and enter a prompt to get started!

Serving this model from Text Generation Inference (TGI)

It's recommended to use TGI version 1.1.0 or later. The official Docker container is: ghcr.io/huggingface/text-generation-inference:1.1.0

Example Docker parameters:

--model-id TheBloke/llemma_7b-GPTQ --port 3000 --quantize gptq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096

Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):

pip3 install huggingface-hub

from huggingface_hub import InferenceClient

endpoint_url = "https://your-endpoint-url-here"

prompt = "Tell me about AI"
prompt_template=f'''{prompt}
'''

client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
                                  max_new_tokens=128,
                                  do_sample=True,
                                  temperature=0.7,
                                  top_p=0.95,
                                  top_k=40,
                                  repetition_penalty=1.1)

print(f"Model output: {response}")

How to use this GPTQ model from Python code

Install the necessary packages

Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.

pip3 install transformers optimum
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
git checkout v0.4.2
pip3 install .

You can then use the following code

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

model_name_or_path = "TheBloke/llemma_7b-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-32g-actorder_True"
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'''{prompt}
'''

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 and Mistral 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: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: EleutherAI's Llemma 7B

ArXiv | Models | Data | Code | Blog | Sample Explorer

Zhangir Azerbayev, Hailey Schoelkopf, Keiran Paster, Marco Dos Santos, Stephen McAleer, Albert Q. Jiang, Jia Deng, Stella Biderman, Sean Welleck

Llemma 7B is a language model for mathematics. It was initialized with Code Llama 7B weights, and trained on the Proof-Pile-2 for 200B tokens.

This model also comes in a 34B parameter version: Llemma 34B.

Evaluations

Llemma models are particularly strong at chain-of-thought mathematical reasoning and using computational tools for mathematics, such as Python and formal theorem provers.

Chain-of-thought Math

On chain-of-thought mathematics tasks, Llemma models outperform Llama-2, Code Llama, and when controlled for model size, outperform Minerva.

Model	Size	GSM8k	OCW	MMLU-STEM	SAT	MATH
Llama 2	7B	11.8%	3.7%	29.9%	25%	3.2%
Code Llama	7B	10.5%	4.4%	25.1%	9.4%	4.5%
LLEMMA	7B	36.4%	7.7%	37.7%	53.1%	18.0%
Minerva	8B	16.2%	7.7%	35.6%	-	14.1%
------------	------	--------	-------	-----------	-------	-------
Code Llama	34B	29.6%	7.0%	40.5%	40.6%	12.2%
LLEMMA	34B	51.5%	11.8%	49.0%	71.9%	25.0%
------------	------	--------	-------	-----------	-------	-------
Minerva	62B	52.4%	12.0%	53.9%	-	27.6%
Minerva	540B	58.8%	17.6%	63.9%	-	33.6%

Further performance can be extracted by using majority voting:

Model	Size	GSM8k maj@100	OCW maj@100	MMLU-STEM maj@16	SAT maj@16	MATH maj@256
LLEMMA	7B	54.0%	14.3%	49.9%	78.1%	33.5
Minerva	8B	28.4%	12.5%	43.4%	-	25.4%
---------	------	-------------	-----------	-----------------	-----------	------------
LLEMMA	34B	69.3%	18.4%	59.7%	81.3%	43.1%
---------	------	-------------	-----------	-----------------	-----------	------------
Minerva	62B	68.5%	23.5%	63.5%	-	43.4%
Minerva	540B	78.5%	30.8%	75.0%	-	50.3%

Tool Use and Theorem Proving

In addition to chain-of-thought reasoning, Llemma has strong capabilities in computational mathematics tasks. For tool use and formal theorem proving evaluations, see our paper.

Citation

@misc{azerbayev2023llemma,
      title={Llemma: An Open Language Model For Mathematics}, 
      author={Zhangir Azerbayev and Hailey Schoelkopf and Keiran Paster and Marco Dos Santos and Stephen McAleer and Albert Q. Jiang and Jia Deng and Stella Biderman and Sean Welleck},
      year={2023},
      eprint={2310.10631},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}