How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.
MiniCPM is a collection of small language models designed for local, on-device deployment in resource-constrained environments. The project focuses on running dense Transformer models on consumer hardware, including GPUs, CPUs, and Apple Silicon, without requiring custom code forks. The project distinguishes itself through heavy optimization for edge hardware, utilizing quantized weight compression in GGUF and MLX formats to reduce memory overhead. It implements advanced inference techniques such as speculative sampling and radix-tree prefix caching to accelerate generation speed and throughp
An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of Dark Experience for General Continual Learning
ICLR 2025 Self-Normalized Resets for Plasticity in Continual Learning
The Code for "The Lie of the Average: How Class Incremental Learning Evaluation Deceives You?"
Xiangkun Wang 1   Junbo Zhang 3   Tianrui Li 4   Xin Yang 1  
The main features of aignlai/gddsg are: Model Adaptation and Merging.
Open-source alternatives to aignlai/gddsg include: openbmb/minicpm — MiniCPM is a collection of small language models designed for local, on-device deployment in resource-constrained… aimagelab/mammoth — An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of Dark Experience for… ajozefiak/selfnormalizedresets — [ICLR 2025] Self-Normalized Resets for Plasticity in Continual Learning. alichr/c3pr — This repository contains the implementation for the paper titled "Canonical Shape Projection is All You Need for 3D… alviur/ldc — Learnable drift compensation (LDC) reduces semantic drift in continual learning using a trainable projector to map… aignlai/edge — The Code for "The Lie of the Average: How Class Incremental Learning Evaluation Deceives You?".