louisbrulenaudet
Research in business taxation and development (NLP, LLM, Computer vision...), University Dauphine-PSL 📖 | Backed by the Microsoft for Startups Hub program
Université Paris-Dauphine (Paris Sciences et Lettres - PSL)Paris
Pinned Repositories
apple-ocr
Easy-to-Use Apple Vision wrapper for text extraction, scalar representation and clustering using K-means.
balena
BALanced Execution through Natural Activation : a human-computer interaction methodology for code running.
docutron
Docutron Toolkit: detection and segmentation analysis for legal data extraction over documents.
manatee
MAnATee(lm) : Market Analysis based on language model architectures.
mergeKit
Tools for merging pretrained Large Language Models and create Mixture of Experts (MoE) from open-source models.
mswp
Decorator that automatically clears temporary local variables upon function execution, effectively preventing clutter and mitigating memory leaks.
ragoon
High level library for batched embeddings generation, blazingly-fast web-based RAG and quantized indexes processing âš¡
srisaurus
Ultralight, non-dependent and minimalist open-source package to recursively generate subresource integrity (SRI) hashes.
totpsaurus
Ultralight, non-dependent and minimalist open-source package for generating Time-based One-Time Passwords (TOTPs), creating OTP URLs, and generating secure backup codes for account recovery.
tsdae
Tranformer-based Denoising AutoEncoder for Sentence Transformers Unsupervised pre-training.
louisbrulenaudet's Repositories
louisbrulenaudet/ragoon
High level library for batched embeddings generation, blazingly-fast web-based RAG and quantized indexes processing âš¡
louisbrulenaudet/balena
BALanced Execution through Natural Activation : a human-computer interaction methodology for code running.
louisbrulenaudet/mergeKit
Tools for merging pretrained Large Language Models and create Mixture of Experts (MoE) from open-source models.
louisbrulenaudet/tsdae
Tranformer-based Denoising AutoEncoder for Sentence Transformers Unsupervised pre-training.
louisbrulenaudet/manatee
MAnATee(lm) : Market Analysis based on language model architectures.
louisbrulenaudet/mswp
Decorator that automatically clears temporary local variables upon function execution, effectively preventing clutter and mitigating memory leaks.
louisbrulenaudet/embeddings-visualizer
Tool designed to help researchers and developers effortlessly visualize and explore their high-dimensional embeddings.
louisbrulenaudet/hf-for-legal
HF for Legal: A Community Package for Legal Applications 🤗
louisbrulenaudet/judilibre-search
API de recherche et de consultation de la plateforme JUDILIBRE.
louisbrulenaudet/mergekit-assistant
Mergekit Assistant is a cutting-edge toolkit designed for the seamless merging of pre-trained language models. It supports an array of models, offers various merging methods, and optimizes for low-resource environments with both CPU and GPU compatibility.
louisbrulenaudet/transformer-heads
Toolkit for attaching, training, saving and loading of new heads for transformer models
louisbrulenaudet/orca
ORCA: Oceanic Recognition & Classification Application for sea-life analysis systems.
louisbrulenaudet/chronos-forecasting
Chronos: Pretrained (Language) Models for Probabilistic Time Series Forecasting
louisbrulenaudet/client-python
Python client library for Mistral AI platform
louisbrulenaudet/faiss
A library for efficient similarity search and clustering of dense vectors.
louisbrulenaudet/icons
Official open source SVG icon library for Bootstrap.
louisbrulenaudet/legalkit-pipeline
Publication pipeline for French legal codes on 🤗 Datasets from LegiFrance with concurrent upload and dynamic REAMDE.md.
louisbrulenaudet/LLaMA-Factory
Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)
louisbrulenaudet/louisbrulenaudet
Config files for my GitHub profile.
louisbrulenaudet/MergeKitCLI
Tools for merging pretrained large language models.
louisbrulenaudet/mteb
MTEB: Massive Text Embedding Benchmark
louisbrulenaudet/neotexto
NeoTexto - A new way to improve your foreign language skills.
louisbrulenaudet/ollama
Get up and running with Llama 3, Mistral, Gemma, and other large language models.
louisbrulenaudet/sentence-transformers
Multilingual Sentence & Image Embeddings with BERT
louisbrulenaudet/stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
louisbrulenaudet/tax-retrieval-benchmark
An implementation of the TaxRetrievalBenchmark task for the 🤗 Massive Text Embedding Benchmark (MTEB) framework.
louisbrulenaudet/tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
louisbrulenaudet/unsloth
Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
louisbrulenaudet/whisper
Robust Speech Recognition via Large-Scale Weak Supervision
louisbrulenaudet/WizardLM
LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath