TimeStress is a dataset designed to evaluate the temporal representation of facts in large language models (LLMs) by assessing their ability to distinguish between correct and incorrect factual statements contextualized with a date and formatted as questions, such as “In 2011, who was the president of the USA? Barack Obama”. The evaluation principle is that […]
Microtune is an autonomous agent that dynamically controls the size of the memory cache used by a relational database (tested on MariaDB). Its objective (FinOps) is to minimize the memory footprint while respecting a maximum latency constraint not to be exceeded. This agent works externally to the database with a SQL link to change the […]
WikiFactDiff is a dataset designed as a resource to perform atomic factual knowledge updates on language models, with the goal of aligning them with current knowledge. It describes the evolution of factual knowledge between two dates, named T_old and T_new, in the form of semantic triples. To enable the possibility of evaluating knowledge algorithms (such […]
Machine learning, in its various tasks from fitting to inference, can be highly energy intensive and raises growing environmental concerns. This situation inspired different initiatives fostering a more frugal, greener AI. Beyond the implementation of good practices, it appears pivotal for researchers and data engineers to gather an empiric knowledge of energy consumption per task, […]
Marine Detect is an innovative project that leverages Deep Learning technology to advance the detection and identification of marine species. These models were developed in the context of the Let’s Revive project in partnership with Tēnaka. Tēnaka emphasizes impact measurement through Tēnaka Science, a platform sharing monthly coral ecosystems data. To automate data collection, Orange […]
Speech processing models are computationally expensive, generating environmental concerns because of their high energy consumption. ESSL (Efficient Self-Supervised Learning) addresses this issue, enabling pretraining with a single GPU for only 28 hours. The reduction in computational costs represents up to two orders of magnitude improvement against existing speech models. Its source code is available on […]
This software implements a video coding algorithm based on neural networks. It is implemented in python using the PyTorch framework. The neural networks are pre-trained and allow video encoding at rates around 1 Mbit/s. It is the reflection of 2 publications presented at international conferences: Conditional Coding for Flexible Learned Video Compression (ICLR 2021) [1][2] […]
A low-impact internal latency measurement tool for OpenAirInterface 5G should provide low latency transmissions for new services (e.g. Industry 4.0). The measurement of such latencies inside the access network is a challenge for which LatSeq is designed. LatSeq is an open-source tool for fine-grained analysis of latency inside the OpenAirInterface base station. This tool is […]
Fiware is an Open Source platform and Orion is its broker component that handles NGSI entities and subscriptions. Orion is heavily used inside the PIXEL europen project and widely used to collect data from IoT and so on. python-orion-client is a Fiware Orion API Python client implementation. It comes along with helpers to handle NGSI […]
The NMaaS (Network Monitoring as a Service) is an open source platform which enables to deploy and manage containerized applications on a pool of servers. This environment is oriented towards the management of network tests, of which it will graphically report the metrics collected in real time. It is more precisely a collection of open […]