metadata

language:
  - en
  - de
license: cc-by-nc-4.0
library_name: transformers
tags:
  - finetune
  - dpo
  - Instruct
  - augmentation
  - german
datasets:
  - argilla/distilabel-math-preference-dpo
pipeline_tag: text-generation
model-index:
  - name: SauerkrautLM-SOLAR-Instruct
    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: 70.82
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-SOLAR-Instruct
          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: 88.63
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-SOLAR-Instruct
          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: 66.2
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-SOLAR-Instruct
          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: 71.95
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-SOLAR-Instruct
          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: 83.5
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-SOLAR-Instruct
          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: 64.14
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-SOLAR-Instruct
          name: Open LLM Leaderboard

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

Overview of all SauerkrautLM-SOLAR-Instruct models
Model Details
Evaluation
Disclaimer
Contact
Collaborations
Acknowledgement

All SauerkrautLM-SOLAR-Instruct Models

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

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:

### System:\nDu sprichst grammatikalisch korrektes Deutsch auf höchstem Muttersprachler Niveau.\n### User:\n{user}\n\n### Assistant:\n{assistant}

*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! Many thanks to TheBloke for super fast quantifying all of our models.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	74.21
AI2 Reasoning Challenge (25-Shot)	70.82
HellaSwag (10-Shot)	88.63
MMLU (5-Shot)	66.20
TruthfulQA (0-shot)	71.95
Winogrande (5-shot)	83.50
GSM8k (5-shot)	64.14

VAGOsolutions
/

SauerkrautLM-SOLAR-Instruct