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  
Code implementation for "Continual Semi-Supervised Learning through Contrastive Interpolation Consistency"
The Code for "The Lie of the Average: How Class Incremental Learning Evaluation Deceives You?"
An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of Dark Experience for General Continual Learning
Las características principales de aimagelab/mammoth son: Continual Learning Frameworks, Model Adaptation and Merging.
Las alternativas de código abierto para aimagelab/mammoth 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/cssl — Code implementation for "Continual Semi-Supervised Learning through Contrastive Interpolation Consistency". aimagelab/lider — Official implementation of "On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning". ajozefiak/selfnormalizedresets — [ICLR 2025] Self-Normalized Resets for Plasticity in Continual Learning. aignlai/edge — The Code for "The Lie of the Average: How Class Incremental Learning Evaluation Deceives You?".