Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"
☆31Nov 4, 2024Updated last year
Alternatives and similar repositories for LiNeS
Users that are interested in LiNeS are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]☆53Dec 22, 2025Updated 7 months ago
- Representation Surgery for Multi-Task Model Merging. ICML, 2024.☆49Oct 10, 2024Updated last year
- ☆219Feb 3, 2024Updated 2 years ago
- Using experimental methods to merge large language models☆11Jul 11, 2026Updated 3 weeks ago
- The official repository of ECCV 2024 paper "Outlier-Aware Test-time Adaptation with Stable Memory Replay"☆22Jun 8, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Code and benchmark for the paper: "A Practitioner's Guide to Continual Multimodal Pretraining" [NeurIPS'24]☆62Dec 10, 2024Updated last year
- ☆13Feb 11, 2026Updated 6 months ago
- Official implementation and dataset for the NAACL 2024 paper "ComCLIP: Training-Free Compositional Image and Text Matching"☆37Aug 18, 2024Updated last year
- LoFiT: Localized Fine-tuning on LLM Representations☆45Jan 15, 2025Updated last year
- ☆19Jan 3, 2025Updated last year
- The repository for our paper: Neighboring Perturbations of Knowledge Editing on Large Language Models☆16May 4, 2024Updated 2 years ago
- ☆14Mar 31, 2024Updated 2 years ago
- BASALT Benchmark datasets, evaluation code and agent training example.☆22Nov 29, 2023Updated 2 years ago
- [ICLR 2025] Official PyTorch implementation of "DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation"☆26Jul 11, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [NeurIPS 2024] For paper Parameter Competition Balancing for Model Merging☆48Oct 11, 2024Updated last year
- Official implementation for 'Sparse denoising diffusion for large graph generation'☆81Aug 18, 2025Updated 11 months ago
- Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner☆31Jun 27, 2024Updated 2 years ago
- MiSS is a novel PEFT method that features a low-rank structure but introduces a new update mechanism distinct from LoRA, achieving an exc…☆35Mar 9, 2026Updated 5 months ago
- ☆30May 9, 2024Updated 2 years ago
- Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic☆32Feb 18, 2026Updated 5 months ago
- StyleTTS 2 Optimized Training Fork☆32Feb 2, 2025Updated last year
- ☆31Oct 29, 2024Updated last year
- ☆14May 9, 2024Updated 2 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆14Mar 4, 2024Updated 2 years ago
- Implementation of OpenAI paper with Simple Noise Scale on Fastai V2☆19Apr 16, 2021Updated 5 years ago
- ICCV 2023 - AdaptGuard: Defending Against Universal Attacks for Model Adaptation☆11Dec 23, 2023Updated 2 years ago
- Active Learning in the era of Foundation Models☆14Apr 16, 2025Updated last year
- Mixtral finetuning☆19Feb 2, 2024Updated 2 years ago
- Generate custom text files for dataloader within UDA methods☆14May 24, 2023Updated 3 years ago
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆82Mar 1, 2025Updated last year
- The official implementation of InterBERT☆11Oct 18, 2022Updated 3 years ago
- Code for the paper "Function-Space Learning Rates"☆23Jun 3, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- DiWA: Diverse Weight Averaging for Out-of-Distribution Generalization☆31Jan 31, 2023Updated 3 years ago
- Official code for ICLR 2024 paper, "A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation"☆86Apr 21, 2024Updated 2 years ago
- Official code for our paper, "LoRA-Pro: Are Low-Rank Adapters Properly Optimized? "☆150Apr 8, 2025Updated last year
- ☆14Aug 15, 2024Updated last year
- ☆36Aug 23, 2023Updated 2 years ago
- [ICLR 2024] Towards Elminating Hard Label Constraints in Gradient Inverision Attacks☆14Feb 6, 2024Updated 2 years ago
- ☆16Jul 9, 2025Updated last year