Spaces:

masonbarnes

/

open-llm-search

like 1

Runtime error

Open LLM search is a custom-tuned Llama 7B model designed to compile text from multiple live search results into a few concise paragraphs. It's completely open-source and a great alternative to Bing, Perplexity, or Bard. Self-hosting the model has become too expensive and we've had to turn off the model for now. We are in desperate need of a small GPU that can run a 7B large language model (~13 GB).

Help would be very appreciated!