LLM4All

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:
- The Multispeech team focused on speech, audio and multimodal signal processing
- The Synalp team (leader of LLM4All) specialized in Natural Language Processing

with a strong support from the Hugginface company on LLM training.

Nb	Leader	Name
WP0	LORIA	Project management
WP1	LORIA	Fine-tuning, continual updating
WP2	LIX	Low-cost LLMs
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

2nd November 2023
- Discussion about progress in FT and CL of LLMs
- Data Management Plan: the DMP is online here or from the top menu
- TODO everyone (for mid-january): complete a first version by editing this markdown file or by sending me your updates by email
7th December 2023
11th January 2024