adapters

A Unified Library for Parameter-Efficient and Modular Transfer Learning

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

Trankit is a Light-Weight Transformer-based Python Toolkit for Multilingual Natural Language Processing

PyTorch code for "VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks" (CVPR2022)

Collection of Tools and Papers related to Adapters / Parameter-Efficient Transfer Learning/ Fine-Tuning

Research code for "What to Pre-Train on? Efficient Intermediate Task Selection", EMNLP 2021

Code of NAACL 2022 "Efficient Hierarchical Domain Adaptation for Pretrained Language Models" paper.

Cross-platform AI agent and chatbot runtime with a Rust core, Python plugins, and normalized adapters.

[CVPR 2026] Official PyTorch implementation of "Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adapters" (TOGA).

lm15 Python reference implementation — provider-neutral, low-level foundation for LLM APIs. Legacy 0.2.x on the legacy-0.2 branch.

X-MIC: Cross-Modal Instance Conditioning for Egocentric Action Generalization, CVPR 2024

Code for EACL'23 paper "Udapter: Efficient Domain Adaptation Using Adapters"

This repositary hosts my experiments for the project, I did with OffNote Labs.

Small Library of PyTorch Adaptation modules

Systems submitted to IWSLT 2022 by the MT-UPC group.

Integration of Adapters into HuggingFace's Transformers (implemented in TensorFlow 2.0)

A vibe-coded open-source re-implementation of Thinking Machines' Tinker API

Helix-v2 1B bilingual hybrid LLM - Nvidia

Master Thesis on "Comparing Modular Approaches for Parameter-Efficient Fine-Tuning"

Ready-to-run training scripts for Transformers and Adapters on >50 NLP tasks