Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"
-
Updated
Mar 10, 2024 - Python
#
parameter-efficient
Here are 16 public repositories matching this topic...
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.
keras-tutorials machine-learning-api keras-models keras-classification-models keras-layer keras-neural-networks keras-visualization keras-tensorflow keras-image-classifier keras-implementations keras-deep-dream keras-tutorial keras-examples keras-neural-network keras-generators keras-deep-learning keras-image-augmentation parameter-efficient-learning parameter-efficient
-
Updated
Aug 16, 2024 - Python
A parameter-efficient mixture-of-experts module for computational pathology - ICLR
digital-pathology iclr pathology computational-pathology multiple-instance-learning mixture-of-experts parameter-efficient
-
Updated
May 17, 2026 - Python
Frame Flexible Network (CVPR2023)
-
Updated
Apr 21, 2023 - Python
ENGRAFT: write facts into an LLM's n-gram (Engram) memory table as a removable overlay: 100 facts in a 9 MB file, no weights touched, verified on llama.cpp GGUF (Qwen3.8-Flash-Next).
ngram interpretability mixture-of-experts memory-editing engram knowledge-injection llm parameter-efficient model-editing knowledge-editing llama-cpp qwen gguf deepseek
-
Updated
Sep 30, 2026 - Python
PEFT-compatible SingLoRA: single-matrix low-rank adaptation with half the adapter parameters of standard LoRA, drop-in for transformers workflows.
adapter machine-learning deep-learning transformers pytorch lora fine-tuning peft llm parameter-efficient singlora
-
Updated
Sep 27, 2026 - Python
Official source code for the paper "Tailored Design of Audio-Visual Speech Recognition Models using Branchformers"
audio-visual-speech-recognition interpretability visual-speech-recognition lipreading robust-asr parameter-efficient
-
Updated
Feb 24, 2025 - Python
Toward controlled evolution of artificial intelligence through validated neural grafting.
artificial-intelligence ai-safety continual-learning modular-ai parameter-efficient llm-training model-grafting auditable-ai controlled-ai drm-transformer saint-g neural-grafting validation-gated graft-registry
-
Updated
May 26, 2026 - Python
ASSTF (Adaptive State-Space Transfer Function): A PyTorch framework for dynamic neural topology that reduces parameters by 5-10x, enables test-time adaptation, and outperforms static models on structure-sensitive tasks.
python machine-learning deep-learning pytorch personalization bilevel-optimization concept-drift anomaly-detection model-compression neural-architecture-search continual-learning few-shot-learning edge-ai edge-deployment on-device-ai adaptive-neural-networks test-time-adaptation parameter-efficient low-rank-adaptation dynamic-topology
-
Updated
Jul 7, 2026 - Python
Various LoRA adapters. One shared basis. Up to 122× compression at scale.
-
Updated
Apr 11, 2026 - Python
Train the smallest LM you can that fits in 16MB. Best model wins!
-
Updated
Mar 24, 2026 - Python
How many parameters are needed to get 99% on MNIST? Personal record of 697 parameters.
-
Updated
Aug 8, 2023 - Python
Reduce LLM inference compute by 4x with no accuracy loss. Oscillatory adapter for pretrained Transformers.
adapter deep-learning transformers pytorch kuramoto parameter-efficient test-time-scaling oscillatory-dynamics
-
Updated
Apr 16, 2026 - Python
A modular and extensible LoRA fine-tuning framework for question-answering tasks with PEFT integration
machine-learning transformers pytorch question-answering lora fine-tuning peft parameter-efficient generative-ai
-
Updated
Jul 15, 2025 - Python
BiDoRA: Bi-Level Optimization for Parameter-Efficient Fine-Tuning of LLMs - Optimized for 3D Code Generation
-
Updated
Mar 26, 2026 - Python
Add this topic to your repo
To associate your repository with the parameter-efficient topic, visit your repo's landing page and select "manage topics."