Service operation

Technical details aspects

Who created PreGPT 2.0?

The backend is managed by Salad.com, Venice.AI and Presearch in tandem.

What is used to Power PreGPT 2.0 ?

PreGPT 2.0 is fueled by Salad.com’s and Venice.AI's decentralized network of GPU nodes. For more insights into Salad's distributed cloud technology, visit their blog and website. For information about Venice.AI visit their website.

What is the underlying LLM model ?

PreGPT 2.0 currently uses the Mistral 7B LLM model and models from Venice.AI.

Is PreGPT 2.0 built from open source components?

Many parts of PreGPT 2.0, including the LLMs and the UI (forked from Hugging Face), are open-sourced. The inference endpoints are hosted by Salad.com.

What are the downtime expectations?

While we aim for consistent uptime, occasional downtime may occur due to high demand.

What are the limitations of PreGPT 2.0 ?

Like all chatbots, PreGPT has its boundaries. It does not provide real-time or web-based information and operates with knowledge up until roughly Spring 2023, when the Mistral 7B training data ended. The current LLM model primarily supports English, with limited capabilities in other languages.