-
LettrIA
- Paris
-
05:32
(UTC +02:00) - https://jplu.github.io/
- https://orcid.org/0000-0002-7876-3441
- @julienplu
Stars
Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity
Open-source Windows and Office activator featuring HWID, Ohook, TSforge, and Online KMS activation methods, along with advanced troubleshooting.
Langchain-powered natural language interface to knowledge-graphs.
List of corpora annotated for coreference for different languages
Robust recipes to align language models with human and AI preferences
KarelDO / wl-coref
Forked from vdobrovolskii/wl-corefState-of-the-art efficient coreference. This repository contains the code for the CRAC-2023 paper "CAW-coref: Conjunction-Aware Word-level Coreference Resolution". Forked from the EMNLP-2021 paper …
A pythonic library providing light-weighted interface with LLMs
Dynamic, resilient AI orchestration. Coordinate data, models, and compute as you build AI workflows.
🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools
ClearML - Model-Serving Orchestration and Repository Solution
Pipeline for pulling and processing online language model pretraining data from the web
Unofficial golang package for the Triton Inference Server(https://github.com/triton-inference-server/server)
The Tensor Algebra SuperOptimizer for Deep Learning
This is the code for our KILT leaderboard submissions (KGI + Re2G models).
🎓 Sharing machine learning course / lecture notes.
Python programs, usually short, of considerable difficulty, to perfect particular skills.
Understanding 'Things' using Semantic Graph Classification (Udacity ML Capstone)
An NLP system for generating reading comprehension questions
A collection of libraries to optimise AI model performances
Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀
Efficient interpolation-based ranking on CPUs
Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptatio…