The LAION (Large-scale Artificial Intelligence Open Network) community, which develops tools, models and data collections for creating free machine learning systems (for example, the LAION collection is used to train models of the Stable Diffusion image synthesis system), presented the first release of the Open-Assistant project, which develops an artificial intelligence chatbot capable of understanding and answering questions in natural language, interacting with third-party systems and dynamically extracting the necessary information.
The project code is written in Python and distributed under the Apache 2.0 license. OpenAssistant developments can be used to create your own intelligent assistants and dialog systems that are not tied to external APIs and services. Conventional consumer hardware is enough to run, for example, it is possible to work on a smartphone.
In addition to the code for training and organizing the work of the bot on its equipment, a collection of already trained ready-made models and a language model are proposed for use, trained on the basis of 600 thousand examples of request-response (instruction-execution) dialogs prepared and reviewed with the involvement of the enthusiast community. An online service was also launched to assess the quality of the chatbot, which uses the OA_SFT_Llama_30B_6 knowledge model, covering 30 billion parameters.
To increase the efficiency of the system and avoid the need to store large amounts of predefined parameters, the project provides for the possibility of using a dynamically updated knowledge base that can retrieve the required information through search engines or external services. For example, when generating responses, the bot can access external APIs to obtain additional data. Of the advanced features, personalization support is also noted, i.e. the ability to adapt to a specific user based on his previous phrases.
The project does not plan to stop at repeating the capabilities of ChatGPT. It is expected that Open-Assistant will spur the development of open development in the field of content generation and query processing in natural languages, just as the open source Stable Diffusion project stimulated the development of tools for generating images.
Source: opennet.ru