We introduce the first 10.7 billion (B) parameter model, SOLAR-10.7B. It's compact, yet remarkably powerful, and demonstrates unparalleled state-of-the-art performance in models with parameters under 30B.

We developed the Depth Up-Scaling technique. Built on the Llama2 architecture, SOLAR-10.7B incorporates the innovative Upstage Depth Up-Scaling. We then integrated Mistral 7B weights into the upscaled layers, and finally, continued pre-training for the entire model.

Depth-Upscaled SOLAR-10.7B has remarkable performance. It outperforms models with up to 30B parameters, even surpassing the recent Mixtral 8X7B model. For detailed information, please refer to the experimental table ([link to be updated soon]). Solar 10.7B is an ideal choice for fine-tuning. SOLAR-10.7B offers robustness and adaptability for your fine-tuning needs. Our simple instruction fine-tuning using the SOLAR-10.7B pre-trained model yields significant performance improvements. [[link to be updated soon]]

This model is pre-trained and is capable of just generating random text. To use it for chatting, you must fine-tune the model first.

Make sure you have the correct version of the transformers library installed:

Use the following Python code to load the model:

To generate text, use the following Python code:

Upstage is creating the best LLM and DocAI. Please find more information at https://upstage.ai

Any questions and suggestions, please use the discussion tab. If you want to contact us directly, drop an email to contact@upstage.ai