SauerkrautLM-14b-MoE-LaserChat

VAGO solutions SauerkrautLM-14b-MoE-LaserChat

Introducing SauerkrautLM-14b-MoE-LaserChat – our Sauerkraut (2x7b) 14b MoE version of the powerful SauerkrautLM-7b-LaserChat and yam-peleg/Experiment26-7B !

By combining the two models, we were able to significantly increase both the German and English language skills. In addition, the initial SauerkrautLM-7b-LaserChat also acts as an adapter for Experiment26-7B, which means it benefits from the chat capabilities of the SauerkrautLM-7b-LaserChat. At the same time, the SauerkrautLM-7b-LaserChat benefits from the knowledge and creativity of Experiment26-7B.

The model SauerkrautLM-14b-MoE-LaserChat is a joint effort between VAGO solutions and Hyperspace.ai. Much appreciation goes to the tremendous research effort of Fernando Fernandes Neto, David Golchinfar and Eric Hartford on their laserRMT approach. Without their independent research collaboration this model release would not have been possible.

Table of Contents

1. Overview of all SauerkrautLM-14b-MoE-LaserChat models
2. Model Details
   • Prompt template
3. Evaluation
4. Disclaimer
5. Contact
6. Collaborations
7. Acknowledgement

All SauerkrautLM-14b-MoE-LaserChat Models

Model Details

SauerkrautLM-14b-MoE-LaserChat

• Model Type: SauerkrautLM-14b-MoE-LaserChat is a MoE Model based on SauerkrautLM-7b-LaserChat and yam-peleg/Experiment26-7B
• Language(s): German, English
• License: Apache 2.0
• Contact: VAGO solutions, Hyperspace.computer

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

Prompt Template:

GPT4 Correct User: Hallo, wie geht es dir?<|end_of_turn|>GPT4 Correct Assistant: Hallo! Ich bin ein künstliches Intelligenzsystem und habe keine persönlichen Gefühle oder körperliche Zustände. Wie kann ich Ihnen helfen?<|end_of_turn|>GPT4 Correct User: Ich benötige nur einen kurzen Satz, den ich in das Prompt Template veröffentlichen kann.<|end_of_turn|>GPT4 Correct Assistant:

GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hello! How can I help you today? If you have any questions or need assistance, feel free to ask.<|end_of_turn|>GPT4 Correct User: I just need a short sentence to post in the prompt template.<|end_of_turn|>GPT4 Correct Assistant:

Evaluation

Open LLM Leaderboard:

benchmarked on lm-evaluation-harness 0.4.1

Performance

<details><summary>Details of AGIEval, GPT4All, TruthfulQA, BigBench </summary>

AGIEval

Average: 44.38%

GPT4All

Average: 74.76%

TruthfulQA

Average: 58.57%

Bigbench

Average: 47.98%

</details>

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 websites. We are also grateful for your feedback and suggestions.  

Collaborations

We are also keenly seeking support and investment for our startups, VAGO solutions and Hyperspace 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, Hyperspace.computer

Acknowledgement

Many thanks to yam-peleg for providing such valuable model to the Open-Source community