TheBloke/SauerkrautLM-SOLAR-Instruct-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)

---

SauerkrautLM SOLAR Instruct - GPTQ

• Model creator: VAGO solutions
• Original model: SauerkrautLM SOLAR Instruct

Description

This repo contains GPTQ model files for VAGO solutions's SauerkrautLM SOLAR Instruct.

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 files were quantised using hardware kindly provided by Massed Compute.

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
• VAGO solutions's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

Prompt template: User-Assistant-Newlines

### User:
{prompt}

### Assistant:

Known compatible clients / servers

GPTQ models are currently supported on Linux (NVidia/AMD) and Windows (NVidia only). macOS users: please use GGUF models.

These GPTQ models are known to work in the following inference servers/webuis.

• text-generation-webui
• KoboldAI United
• LoLLMS Web UI
• Hugging Face Text Generation Inference (TGI)

This may not be a complete list; if you know of others, please let me know!

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 and Mistral models in 4-bit.

Branch	Bits	GS	Act Order	Damp %	GPTQ Dataset	Seq Len	Size	ExLlama	Desc
main	4	128	Yes	0.1	VMware Open Instruct	8192	5.98 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	VMware Open Instruct	8192	6.59 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	VMware Open Instruct	8192	11.01 GB	No	8-bit, with Act Order. No group size, to lower VRAM requirements.
gptq-8bit-128g-actorder_True	8	128	Yes	0.1	VMware Open Instruct	8192	11.25 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	VMware Open Instruct	8192	11.99 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	VMware Open Instruct	8192	6.18 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/SauerkrautLM-SOLAR-Instruct-GPTQ in the "Download model" box.

To download from another branch, add :branchname to the end of the download name, eg TheBloke/SauerkrautLM-SOLAR-Instruct-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 SauerkrautLM-SOLAR-Instruct-GPTQ:

mkdir SauerkrautLM-SOLAR-Instruct-GPTQ
huggingface-cli download TheBloke/SauerkrautLM-SOLAR-Instruct-GPTQ --local-dir SauerkrautLM-SOLAR-Instruct-GPTQ --local-dir-use-symlinks False

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

mkdir SauerkrautLM-SOLAR-Instruct-GPTQ
huggingface-cli download TheBloke/SauerkrautLM-SOLAR-Instruct-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir SauerkrautLM-SOLAR-Instruct-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 Hugging Face 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 SauerkrautLM-SOLAR-Instruct-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/SauerkrautLM-SOLAR-Instruct-GPTQ --local-dir SauerkrautLM-SOLAR-Instruct-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/SauerkrautLM-SOLAR-Instruct-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/SauerkrautLM-SOLAR-Instruct-GPTQ.

   • To download from a specific branch, enter for example TheBloke/SauerkrautLM-SOLAR-Instruct-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: SauerkrautLM-SOLAR-Instruct-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/SauerkrautLM-SOLAR-Instruct-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'''### User:
{prompt}

### Assistant:
'''

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}")

Python code example: inference from this GPTQ model

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 --upgrade transformers optimum
# If using PyTorch 2.1 + CUDA 12.x:
pip3 install --upgrade auto-gptq
# or, if using PyTorch 2.1 + CUDA 11.x:
pip3 install --upgrade auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/

If you are using PyTorch 2.0, you will need to install AutoGPTQ from source. Likewise if you have problems with the pre-built wheels, you should try building from source:

pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
git checkout v0.5.1
pip3 install .

Example Python code

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

model_name_or_path = "TheBloke/SauerkrautLM-SOLAR-Instruct-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 = "Write a story about llamas"
system_message = "You are a story writing assistant"
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, 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 Transformers. For non-Mistral models, AutoGPTQ can also be used directly.

ExLlama is compatible with Llama architecture models (including Mistral, Yi, DeepSeek, SOLAR, etc) in 4-bit. Please see the Provided Files table above for per-file compatibility.

For a list of clients/servers, please see "Known compatible clients / servers", above.

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: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: VAGO solutions's SauerkrautLM SOLAR Instruct

VAGO solutions SauerkrautLM-SOLAR-Instruct

Introducing SauerkrautLM-SOLAR-Instruct – our Sauerkraut version of the powerful upstage/SOLAR-10.7B-Instruct-v1.0 ! Aligned with DPO

Table of Contents

1. Overview of all SauerkrautLM-SOLAR-Instruct models
2. Model Details
   • Prompt template
   • Training Dataset
   • Data Contamination Test
3. Evaluation
4. Disclaimer
5. Contact
6. Collaborations
7. Acknowledgement

All SauerkrautLM-SOLAR-Instruct Models

Model	HF	GPTQ	GGUF	AWQ
SauerkrautLM-SOLAR-Instruct	Link	coming soon	coming soon	coming soon

Model Details

SauerkrautLM-SOLAR-Instruct

• Model Type: SauerkrautLM-SOLAR-Instruct is a finetuned Model based on upstage/SOLAR-10.7B-Instruct-v1.0
• Language(s): English, German
• License: cc-by-nc-4.0
• Contact: Website David Golchinfar

Training Dataset:

SauerkrautLM-SOLAR-Instruct was trained with mix of German data augmentation and translated data. Aligned through DPO with our new German SauerkrautLM-DPO dataset based on parts of the SFT SauerkrautLM dataset as chosen answers and Sauerkraut-7b-HerO as rejected answers. Added with additional translated Parts of the HuggingFaceH4/ultrafeedback_binarized (Our dataset do not contain any TruthfulQA prompts - check Data Contamination Test Results) and argilla/distilabel-math-preference-dpo.
We found, that only a simple translation of training data can lead to unnatural German phrasings. Data augmentation techniques were used to grant grammatical, syntactical correctness and a more natural German wording in our training data.

We improved the German language skills on this model. Nevertheless, certain formulations may occur that are not entirely correct.

Data Contamination Test Results

Some models on the HuggingFace leaderboard had problems with wrong data getting mixed in. We checked our SauerkrautLM-DPO dataset with a special test [1] on this model as target model and upstage/SOLAR-10.7B-Instruct-v1.0 as reference model. The HuggingFace team used the same methods [2, 3].

Our results, with result < 0.1, %: being well below 0.9, indicate that our dataset is free from contamination.

The data contamination test results of HellaSwag and Winograde will be added once [1] supports them.

Dataset	ARC	MMLU	TruthfulQA	GSM8K
SauerkrautLM-DPO	result < 0.1, %: 0.0	result < 0.1, %: 0.09	result < 0.1, %: 0.13	result < 0.1, %: 0.16

[1] https://github.com/swj0419/detect-pretrain-code-contamination

[2] https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard/discussions/474#657f2245365456e362412a06

[3] https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard/discussions/265#657b6debf81f6b44b8966230

Prompt Template:

### User:
Hallo, wie geht es dir?

### Assistant:
Hallo! Es freut mich, dass du mit mir kommunizierst. Ich bin hier, um zu helfen und deine Anfragen zu erfüllen. Du fragst, wie ich mich fühle. Als künstliche Intelligenz habe ich keine eigentlichen Emotionen im Sinne eines Menschen, aber ich funktioniere optimal und bin bereit, Dienste anzubieten.
Wie geht es dir momentan? Können wir zusammen etwas interessantes oder hilfreiches erledigen?

*Prompt Example on Temp 0.5

### User:
Hello, how are you?

### Assistant:
Hi there! I am an AI language model, so I don't have personal feelings or emotions in the traditional sense. However, I can assure you that my systems and processes are functioning well at this moment, allowing me to provide helpful responses for your queries.
How may I assist you today?

*Prompt Example on Temp 0.5

Evaluation

Metric	Value
Avg.	74.21
ARC (25-shot)	70.82
HellaSwag (10-shot)	88.63
MMLU (5-shot)	66.2
TruthfulQA (0-shot)	71.95
Winogrande (5-shot)	83.5
GSM8K (5-shot)	64.14

Disclaimer

We must inform users that despite our best efforts in data cleansing, the possibility of uncensored content slipping through cannot be entirely ruled out. However, we cannot guarantee consistently appropriate behavior. Therefore, if you encounter any issues or come across inappropriate content, we kindly request that you inform us through the contact information provided. Additionally, it is essential to understand that the licensing of these models does not constitute legal advice. We are not held responsible for the actions of third parties who utilize our models.  

Contact

If you are interested in customized LLMs for business applications, please get in contact with us via our website or contact us at Dr. Daryoush Vaziri. We are also grateful for your feedback and suggestions.  

Collaborations

We are also keenly seeking support and investment for our startup, VAGO solutions, where we continuously advance the development of robust language models designed to address a diverse range of purposes and requirements. If the prospect of collaboratively navigating future challenges excites you, we warmly invite you to reach out to us.

Acknowledgement

Many thanks to argilla and Huggingface for providing such valuable datasets to the Open-Source community. And of course a big thanks to upstage for providing the open source community with their latest technology!