- Paris
Highlights
- Pro
Stars
MINT-1T: A one trillion token multimodal interleaved dataset.
Open weights language model from Google DeepMind, based on Griffin.
Schedule-Free Optimization in PyTorch
[ECCV2024] VideoMamba: State Space Model for Efficient Video Understanding
Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
TensorDict is a pytorch dedicated tensor container.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones
Image Encryption and Decryption using AES and Visual Cryptography.
Applying Steganography followed by Visual Cryptography Encode and Decode data
This repository contains demos I made with the Transformers library by HuggingFace.
Official implementation of "When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture" published at NeurIPS 2022.
Solve puzzles. Improve your pytorch.
Code for the paper "Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models"
Structured state space sequence models
Artificial Intelligence and Natural System Design Tool
Stereogram (aka Magic Eye) solver, for people who can't see them .
Demo code for generating autostereograms (aka "Magic Eye" illusions). Includes code to generate the base image, map arbitrary depth mappings, and one hand-generated depth mapping to demonstrate.
Whereabouts Ascertainment for Low-lying Detectable Objects. The SOTA in FOSS AI for drones!
Seamlessly integrate LLMs as Python functions
Heart Rate Variability Training with the Polar H10 Monitor
You like pytorch? You like micrograd? You love tinygrad! ❤️
QLoRA: Efficient Finetuning of Quantized LLMs