--- language: - de - en - it - fr - pt - es license: gemma tags: - spectrum model-index: - name: SauerkrautLM-gemma-2-9b-it results: - task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics: - type: inst_level_strict_acc and prompt_level_strict_acc value: 30.24 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-gemma-2-9b-it name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics: - type: acc_norm value: 43.25 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-gemma-2-9b-it name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics: - type: exact_match value: 0.53 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-gemma-2-9b-it name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics: - type: acc_norm value: 10.29 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-gemma-2-9b-it name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics: - type: acc_norm value: 12.34 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-gemma-2-9b-it name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 34.34 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-gemma-2-9b-it name: Open LLM Leaderboard --- ![SauerkrautLM-gemma-2-9b-it]( https://vago-solutions.ai/wp-content/uploads/2024/08/SauerkrautLM-gemma-2-9b.png "SauerkrautLM-gemma-2-9b-it") ## VAGO solutions SauerkrautLM-gemma-2-9b-it **Fine-tuned Model** - *to showcase the potential of resource-efficient Fine-Tuning of Large Language Models using **Spectrum Fine-Tuning*** Introducing **SauerkrautLM-gemma-2-9b-it** – our Sauerkraut version of the powerful [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it)! - Fine-tuning on German-English data with [**Spectrum**](https://github.com/cognitivecomputations/spectrum) Fine-Tuning **targeting 25% of the layers.** - Utilized unique German-English Sauerkraut Mix v2 - Implemented bespoke, precision-engineered fine-tuning approach # Table of Contents 1. [Overview of all SauerkrautLM-gemma-2-9b-it](#all-SauerkrautLM-gemma-2-9b-it) 2. [Model Details](#model-details) - [Training procedure](#training-procedure) 3. [Evaluation](#evaluation) 5. [Disclaimer](#disclaimer) 6. [Contact](#contact) 7. [Collaborations](#collaborations) 8. [Acknowledgement](#acknowledgement) ## All SauerkrautLM-gemma-2-9b-it | Model | HF | EXL2 | GGUF | AWQ | |-------|-------|-------|-------|-------| | SauerkrautLM-gemma-2-9b-it | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-gemma-2-9b-it) | coming soon | coming soon | coming soon | ## Model Details **SauerkrautLM-gemma-2-9b-it** - **Model Type:** SauerkrautLM-gemma-2-9b-it is a fine-tuned Model based on [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) - **Language(s):** German, English - **License:** gemma - **Contact:** [VAGO solutions](https://vago-solutions.ai) ## Training Procedure This model showcases the potential of resource-efficient fine-tuning of large language models using Spectrum Fine-Tuning. Here's a brief on the procedure: **Fine-tuning on German-English Data**: - Utilized Spectrum Fine-Tuning, targeting 25% of the model's layers - Introduced the model to a unique German-English Sauerkraut Mix v2 - Implemented a bespoke, precision-engineered fine-tuning approach **Sauerkraut Mix v2**: - Premium Dataset for Language Models, focusing on German and English - Meticulously selected, high-quality dataset combinations - Cutting-edge synthetic datasets created using proprietary, high-precision generation techniques ## Objective and Results The primary goal of this training was to demonstrate that with Spectrum Fine-Tuning targeting 25% of the layers, an already strong 9 billion parameter model can be further enhanced while using a fraction of the resources of an ordinary fine-tuning approach. The model has improved in every skill, with significant improvements in instruction-following, common-sense reasoning and math. **Spectrum Fine-Tuning can efficiently enhance a large language model's capabilities while preserving the majority of its previously acquired knowledge.** ## Evaluation **AGIEVAL** ![SauerkrautLM-gemma-2-9b-it-AGIEVAL]( https://vago-solutions.ai/wp-content/uploads/2024/08/AGIEval-gemma9b.png "SauerkrautLM-gemma-2-9b-it-AGIEVAL") **GPT4ALL** ![SauerkrautLM-gemma-2-9b-it-GPT4ALL]( https://vago-solutions.ai/wp-content/uploads/2024/08/GPT4ALL-gemma9b.png "SauerkrautLM-gemma-2-9b-it-GPT4ALL") **TRUTHFULQA** ![SauerkrautLM-gemma-2-9b-it-TRUTHFULQA]( https://vago-solutions.ai/wp-content/uploads/2024/08/TQA-gemma9b.png "SauerkrautLM-gemma-2-9b-it-TRUTHFULQA") **OPENLEADERBOARD 2** ![SauerkrautLM-gemma-2-9b-it-OPENLEADERBOARD]( https://vago-solutions.ai/wp-content/uploads/2024/08/HF2-gemma9b.png "SauerkrautLM-gemma-2-9b-it-OPENLEADERBOARD") **MMLU 5-shot** ![SauerkrautLM-gemma-2-9b-it-MMLU-5shot]( https://vago-solutions.ai/wp-content/uploads/2024/08/MMLU-Gemma9b.png "SauerkrautLM-gemma-2-9b-it-MMLU-5shot") Please be informed that our benchmark results in absolute numbers are different from the Hugging Face Leaderboard, due to different setups in our benchmark evaluation pipeline. However, the relative differences remain the same. ## 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. 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 at [VAGO solutions](https://vago-solutions.ai) ## Acknowledgement Many thanks to [google](https://huggingface.co/google) for providing such a valuable model to the Open-Source community. # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_VAGOsolutions__SauerkrautLM-gemma-2-9b-it) | Metric |Value| |-------------------|----:| |Avg. |21.83| |IFEval (0-Shot) |30.24| |BBH (3-Shot) |43.25| |MATH Lvl 5 (4-Shot)| 0.53| |GPQA (0-shot) |10.29| |MuSR (0-shot) |12.34| |MMLU-PRO (5-shot) |34.34|