-
INRIA, Sorbonne
- Paris, France
-
16:14
(UTC +02:00)
Highlights
- Pro
Block or Report
Block or report ZoeYou
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseStars
Language
Sort by: Recently starred
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
A modular graph-based Retrieval-Augmented Generation (RAG) system
coFR: COreference resolution tool for FRench (and singletons).
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
DSPy: The framework for programming—not prompting—foundation models
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
An opinionated NLP research template
A fun tool for quickly browsing unsourced snippets on Wikipedia.
Overview and tutorial of the LangChain Library
Coreference resolution for English, French, German and Polish, optimised for limited training data and easily extensible for further languages
Doing simple retrieval from LLM models at various context lengths to measure accuracy
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
Question and Answer based on Anything.
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.
The fast python bm25 algorithm implemented with reverted index
SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.
utilities for decoding deep representations (like sentence embeddings) back to text
Large-scale dataset of patent drawings and image retrieval baseline.
Smatch tool: evaluation of AMR semantic structures
A python library that makes AMR parsing, generation and visualization simple.
Toolkit to help understand "what lies" in word embeddings. Also benchmarking!
code for document level AMR representation and evaluation
Generate from English-Centric AMR into Multiple Languages.
Free and Open, Distributed, RESTful Search Engine