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
Xiangkun Wang 1   Junbo Zhang 3   Tianrui Li 4   Xin Yang 1  
An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of Dark Experience for General Continual Learning
The Code for "The Lie of the Average: How Class Incremental Learning Evaluation Deceives You?"
This is the official PyTorch implementation for the paper "Fed-Duet: Dual Expert-Orchestrated Framework for Continual Federated Vision-Language Learning".
Las características principales de cocogt96/fed-duet son: Model Adaptation and Merging.
Las alternativas de código abierto para cocogt96/fed-duet incluyen: openbmb/minicpm — MiniCPM is a collection of small language models designed for local, on-device deployment in resource-constrained… aignlai/gddsg — Xiangkun Wang 1   Junbo Zhang 3   Tianrui Li 4   Xin Yang 1  . 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… aignlai/edge — The Code for "The Lie of the Average: How Class Incremental Learning Evaluation Deceives You?".