LightOn's repositories
dfa-scales-to-modern-deep-learning
Study on the applicability of Direct Feedback Alignment to neural view synthesis, recommender systems, geometric learning, and natural language processing.
double-descent-curve
Double Descent Curve with Optical Random Features
transfer-learning-opu
Optical Transfer Learning
opu-benchmarks
ML benchmarks performance featuring LightOn's Optical Processing Unit (OPU) vs CPU and GPU.
supervised-random-projections
Python implementation of supervised PCA, supervised random projections, and their kernel counterparts.
reinforcement-learning-opu
Code to perform Model-Free Episodic Control using Aurora OPUs
contrastive-embeddings-for-neural-architectures
Architecture embeddings independent from the parametrization of the search space
lightonmuse
Python client for the LightOn Muse API
akronomicon
Public rankings of extreme-scale models
double-trouble-in-double-descent
Double Trouble in the Double Descent Curve with Optical Processing Units.
adversarial-robustness-by-design
A new defense mechanism against adversarial attacks through Optical Processing Units and synthetic gradients.
phase-retrieval-opu
Minimal code to perform phase retrieval on LightOn OPUs
paradigm-client
Python client for LightOn Paradigm
chroma
the AI-native open-source embedding database
composer
Supercharge Your Model Training
muse-examples
Collection of examples for the Muse models.
muse-google-sheets
Source code for the integration of Muse in Google Sheets.
outlines
Structured Text Generation
text-embeddings-inference
A blazing fast inference solution for text embeddings models
text-generation-inference
Large Language Model Text Generation Inference
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs