README.md

---
language:
- en
- de
- fr
- it
- es
license: apache-2.0
library_name: transformers
tags:
- mistral
- finetune
- sft
- dpo
- chatml
- augmentation
- german
- mixtral
- moe
datasets:
- Open-Orca/SlimOrca
- argilla/distilabel-math-preference-dpo
pipeline_tag: text-generation
model-index:
- name: SauerkrautLM-Mixtral-8x7B
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 68.86
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-Mixtral-8x7B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 86.01
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-Mixtral-8x7B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 66.69
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-Mixtral-8x7B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 57.2
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-Mixtral-8x7B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 80.51
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-Mixtral-8x7B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 47.54
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-Mixtral-8x7B
      name: Open LLM Leaderboard
---

![SauerkrautLM](https://vago-solutions.de/wp-content/uploads/2023/12/Sauerkraut_MoE.png "SauerkrautLM-Mixtral-8x7B")
## VAGO solutions SauerkrautLM-Mixtral-8x7B
Introducing **SauerkrautLM-Mixtral-8x7B** – our Sauerkraut version of the powerful Mixtral-8x7B! 
Finetuned and aligned with **SFT** and **DPO**

# Table of Contents
1. [Overview of all SauerkrautLM-Mixtral models](#all-sauerkrautlm-mixtral-models)
2. [Model Details](#model-details)
   - [Prompt template](#prompt-template)
   - [Training Dataset](#training-dataset)
3. [Evaluation](#evaluation)
5. [Disclaimer](#disclaimer)
6. [Contact](#contact)
7. [Collaborations](#collaborations)
8. [Acknowledgement](#acknowledgement)


## All SauerkrautLM-Mixtral Models

| Model | HF    | GPTQ  | GGUF  | AWQ  |
|-------|-------|-------|-------|-------|
| SauerkrautLM-Mixtral-8x7B  | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-Mixtral-8x7B) | [Link](https://huggingface.co/TheBloke/SauerkrautLM-Mixtral-8x7B-GPTQ) | [Link](https://huggingface.co/TheBloke/SauerkrautLM-Mixtral-8x7B-GGUF) | [Link](https://huggingface.co/TheBloke/SauerkrautLM-Mixtral-8x7B-AWQ) |
| SauerkrautLM-Mixtral-8x7B-Instruct  | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-Mixtral-8x7B-Instruct) | [Link](https://huggingface.co/TheBloke/SauerkrautLM-Mixtral-8x7B-Instruct-GPTQ) | [Link](https://huggingface.co/TheBloke/SauerkrautLM-Mixtral-8x7B-Instruct-GGUF) | [Link](https://huggingface.co/TheBloke/SauerkrautLM-Mixtral-8x7B-Instruct-AWQ) |

## Model Details
**SauerkrautLM-Mixtral-8x7B**
- **Model Type:** SauerkrautLM-Mixtral-8x7B is a Mixture of Experts (MoE) Model based on [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) 
- **Language(s):** English, German, French, Italian, Spanish
- **License:** APACHE 2.0
- **Contact:** [Website](https://vago-solutions.de/#Kontakt) [David Golchinfar](mailto:[email protected])

### Training Dataset:

SauerkrautLM-Mixtral-8x7B was trained with mix of German data augmentation and translated data. 
**SFT** with the dataset[OpenOrca/Slim-Orca](https://huggingface.co/datasets/Open-Orca/SlimOrca) and 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](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-HerO) as rejected answers. Added with additional **translated Parts of the [HuggingFaceH4/ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized)** and **[argilla/distilabel-math-preference-dpo](https://huggingface.co/datasets/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. 

### 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 a smaller model for this problem. 
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:
```
<|im_start|>system
Du bist ein großes Sprachmodell, das höflich und kompetent antwortet. Schreibe deine Gedanken Schritt für Schritt auf, um Probleme sinnvoll zu lösen.<|im_end|>
<|im_start|>user
Wie geht es dir?<|im_end|>
<|im_start|>assistant

```
## Evaluation

![Harness](https://vago-solutions.de/wp-content/uploads/2023/12/MoEbenchmark.png "SauerkrautLM-Mixtral-8x7B Harness")
*evaluated with lm-evaluation-harness v0.3.0 - mmlu coming soon

*All benchmarks were performed with a sliding window of 4096. New Benchmarks with Sliding Window null coming soon

## 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. These models may be employed for commercial purposes, and the Apache 2.0 remains applicable and is included with the model files.
 
## 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](mailto:[email protected]). 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 [OpenOrca](https://huggingface.co/Open-Orca), [argilla](https://huggingface.co/datasets/argilla) and [Huggingface](https://huggingface.co) for providing such valuable datasets to the Open-Source community. And of course a big thanks to MistralAI for providing the open source community with their latest technology!
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_VAGOsolutions__SauerkrautLM-Mixtral-8x7B)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |67.80|
|AI2 Reasoning Challenge (25-Shot)|68.86|
|HellaSwag (10-Shot)              |86.01|
|MMLU (5-Shot)                    |66.69|
|TruthfulQA (0-shot)              |57.20|
|Winogrande (5-shot)              |80.51|
|GSM8k (5-shot)                   |47.54|