Embedded graphics library to create beautiful UIs for any MCU, MPU and display type.

Survey: A collection of AWESOME papers and resources on the latest research in Mixture of Experts.

Next-Token Prediction is All You Need

code for paper: {MIST}: Defending Against Membership Inference Attacks Through {Membership-Invariant} Subspace Training

Benchmarking MIAs against LLMs.

Tools for merging pretrained large language models.

This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.

PyTorch library for cost-effective, fast and easy serving of MoE models.

Control Blackmagic Design cameras using Bluetooth Low Energy

Blackmagic Design Camera Control for ESP32 devices (feat. LILYGO T-Display-S3, M5Stack M5CoreS3, M5Stack Basic, M5Stack M5StickC Plus, Freenove ESP32-S3-WROOM

Source code for Document-level Membership Inference for Large Language Models - see https://arxiv.org/pdf/2310.15007

[NeurIPS 2024] "Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration"

Arduino ESP32 Library for connecting to Blackmagic Cameras using Bluetooth Low Energy.

From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)

A fast MoE impl for PyTorch

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)

This is an official repository for Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study (ICCV2023).

[ACM MM23] CLIP-Count: Towards Text-Guided Zero-Shot Object Counting

Understand Human Behavior to Align True Needs

Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

Mamba SSM architecture

SAM: Sharpness-Aware Minimization (PyTorch)

MambaOut: Do We Really Need Mamba for Vision?

Next generation Cosmic desktop environment

[NeurIPS 2024 Oral][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-sim…

Python package for measuring memorization in LLMs.