The article discusses Perplexica, an open-source AI-powered search tool that aims to address the limitations of traditional and proprietary AI-powered search engines. The tool uses large language models (LLMs) like Mixtral and Gemini to understand and process user queries, delivering relevant and insightful results. It allows searches to be conducted locally, ensuring privacy, and employs information retrieval techniques to fetch relevant web pages based on user queries. Perplexica offers focus modes for specific types of questions, including All Mode, Writing Assistant Mode, Academic Search Mode, YouTube Search Mode, and Wolfram Alpha Search Mode.
This model was built using a new Smaug recipe for improving performance on real world multi-turn conversations applied to meta-llama/Meta-Llama-3-70B-Instruct.
The model outperforms Llama-3-70B-Instruct substantially, and is on par with GPT-4-Turbo, on MT-Bench (see below).
The model outperforms Llama-3-70B-Instruct substantially, and is on par with GPT-4-Turbo, on MT-Bench (see below).
OpenAI introduces GPT-4, a new large language model that surpasses human performance on various tasks. Although not yet publicly available, the article provides insights into its capabilities and how it sets a new standard for AI.
hat - chat directly, character card is your prompt
instruct- chat between "you" and "assistant" using the model's prompt format
chat-instruct- chat with you and a character card as a prompt but with the instruct template applied. .i.e "you are an AI playing x character, respond as the character would" converted to alpaca, wizard or whatever
There is no best, but for factual information, you probably want to keep to instruct mode. instruct-chat doesn't necessarily play the characters better or make them write longer. It's sort of hit or miss. one may work better than the other for a particular model and prompt.
instruct- chat between "you" and "assistant" using the model's prompt format
chat-instruct- chat with you and a character card as a prompt but with the instruct template applied. .i.e "you are an AI playing x character, respond as the character would" converted to alpaca, wizard or whatever
There is no best, but for factual information, you probably want to keep to instruct mode. instruct-chat doesn't necessarily play the characters better or make them write longer. It's sort of hit or miss. one may work better than the other for a particular model and prompt.
