Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"

This is the implementation of the paper AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning (https://arxiv.org/abs/2205.12410).

K-CAI NEURAL API - Keras based neural network API that will allow you to create parameter-efficient, memory-efficient, flops-efficient multipath models with new layer types. There are plenty of examples and documentation.

A parameter-efficient mixture-of-experts module for computational pathology

Frame Flexible Network (CVPR2023)

Official source code for the paper "Tailored Design of Audio-Visual Speech Recognition Models using Branchformers"

Toward controlled evolution of artificial intelligence through validated neural grafting.

A modular and extensible LoRA fine-tuning framework for question-answering tasks with PEFT integration

How many parameters are needed to get 99% on MNIST? Personal record of 697 parameters.

Various LoRA adapters. One shared basis. Up to 122× compression at scale.

Train the smallest LM you can that fits in 16MB. Best model wins!

Reduce LLM inference compute by 4x with no accuracy loss. Oscillatory adapter for pretrained Transformers.

BiDoRA: Bi-Level Optimization for Parameter-Efficient Fine-Tuning of LLMs - Optimized for 3D Code Generation

Unified Fine-Tuning Framework: Simplify Parameter-Efficient Fine-Tuning with LoRA, QLoRA, and IA3. Multi-device support for macOS, GPU, and CPU. Production-ready configurations and examples included.