Edit model card

SauerkrautLM

VAGO solutions SauerkrautLM-Mixtral-8x7B-Instruct quantized by Florian Zimmermeister for fp8 usage

Introducing SauerkrautLM-Mixtral-8x7B-Instruct – our Sauerkraut version of the powerful Mixtral-8x7B-Instruct! Aligned with DPO

Table of Contents

  1. Overview of all SauerkrautLM-Mixtral models
  2. Model Details
  3. Evaluation
  4. Disclaimer
  5. Contact
  6. Collaborations
  7. Acknowledgement

All SauerkrautLM-Mixtral Models

Model HF GPTQ GGUF AWQ
SauerkrautLM-Mixtral-8x7B-Instruct Link Link Link Link
SauerkrautLM-Mixtral-8x7B Link Link Link Link

Model Details

SauerkrautLM-Mixtral-8x7B-Instruct

Training Dataset:

SauerkrautLM-Mixtral-8x7B-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.

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:

<s> [INST] Instruction [/INST] Model answer</s> [INST] Follow-up instruction [/INST]

Evaluation

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

German RAG LLM Evaluation corrected result after FIX: https://github.com/huggingface/lighteval/pull/171

|                         Task                         |Version|Metric|Value|   |Stderr|
|------------------------------------------------------|------:|------|----:|---|-----:|
|all                                                   |       |acc   |0.975|±  |0.0045|
|community:german_rag_eval:_average:0                  |       |acc   |0.975|±  |0.0045|
|community:german_rag_eval:choose_context_by_question:0|      0|acc   |0.953|±  |0.0067|
|community:german_rag_eval:choose_question_by_context:0|      0|acc   |0.998|±  |0.0014|
|community:german_rag_eval:context_question_match:0    |      0|acc   |0.975|±  |0.0049|
|community:german_rag_eval:question_answer_match:0     |      0|acc   |0.974|±  |0.0050|

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. 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 MistralAI for providing the open source community with their latest technology!

Downloads last month
23
Safetensors
Model size
46.7B params
Tensor type
BF16
·
F8_E4M3
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train pL-Community/SauerkrautLM-Mixtral-8x7B-Instruct-FP8-Dynamic

Collection including pL-Community/SauerkrautLM-Mixtral-8x7B-Instruct-FP8-Dynamic