Welcome to LLM4All
There are many powerful Large Language Models (LLM) beyond ChatGPT and Bard. We focus in this project on such open-source LLMs that:
- Everyone, preferably with some GPU resources, can deploy in her/his own computers and control in much more depth than ChatGPT and Bard.
- Will be finetuned to better handle human meetings and conversations (but no chatbots!), especially in French.
- Will be incrementally updated with the last pieces of news, emerging lexicon, events.
- Will be connected to the best speech recognition models (Whisper, MMS...) to handle in particular emergency calls in hospitals.
LLM4All is a project funded by the French ANR (Agence Nationale de la Recherche).
The consortium is composed of, in alphabetical order:
- The APHP hospitals in Paris
- The Linagora company in Paris, focused on open-source solutions for language
- The LIX laboratory in Paris:
- The DaSciM team specialized in data analytics and machine learning
- The LORIA laboratory in Nancy:
with a strong support from the Hugginface company on LLM training.
- Start date: Oct 1st, 2023
- Duration: 42 months
|WP1||LORIA||Fine-tuning, continual updating|
|WP3||Linagora||LLMs for spoken dialogue|
|WP4||AP-HP||Boosting LLMs with other data|
|WP5||Linagora||Communication, dissemination, exploitation|
cerisara at loria dot fr
Our PMT meetings occur at 2PM on the first Thrusday of every month at URL https://jitsi.linagora.com/llm4all