Nous Capybara 7B V1.9

About

The Nous Capybara 7B V1.9 is a cutting-edge large language model created by NousResearch, featuring 7 billion parameters. It's an advancement in the Capybara series, utilizing the novel Amplify-Instruct data synthesis technique to create a focused training dataset comprising 20,000 curated conversational examples, most of which include new, innovative tokens. Built on the Mistral architecture, it excels in multi-turn conversations, adeptly summarizing complex topics and recalling information up to late 2022. Despite its innovative framework, it faces challenges due to a smaller dataset, which may limit its generalization and introduce uncertainties related to scalability and biases. Its development is ongoing, with aims to overcome these limitations by expanding the dataset and enhancing contextual understanding.

Capabilities

Providers(2)