Alternatives and similar repositories for transformer-fusion

Users that are interested in transformer-fusion are comparing it to the libraries listed below

• pilancilab / Riemannian_Preconditioned_LoRA
  source code for paper "Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models"
  ☆33Updated last year
• nik-dim / tall_masks
  Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]
  ☆51Updated 3 weeks ago
• Wuyxin / DISC
  (ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation
  ☆43Updated 2 months ago
• PKU-ML / non_neg
  Official Code for ICLR 2024 Paper: Non-negative Contrastive Learning
  ☆46Updated last year
• uiuctml / Localize-and-Stitch
  Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
  ☆32Updated 3 months ago
• tanganke / peta
  Code for paper "Parameter Efficient Multi-task Model Fusion with Partial Linearization"
  ☆24Updated last year
• EnnengYang / AdaMerging
  AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.
  ☆100Updated last year
• DaShenZi721 / HRA
  ☆31Updated last month
• NUS-HPC-AI-Lab / GEOM
  Pytorch implementation of ICML-2024 "Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching"
  ☆26Updated last year
• EnnengYang / RepresentationSurgery
  Representation Surgery for Multi-Task Model Merging. ICML, 2024.
  ☆47Updated last year
• Chaos96 / fourierft
  ☆152Updated last year
• Heidelberg-NLP / CC-SHAP-VLM
  Official code implementation for the paper "Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Expl…
  ☆12Updated 9 months ago
• harveyhuang18 / EMR_Merging
  [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging
  ☆74Updated 10 months ago
• Jiachen-T-Wang / GREATS
  ☆17Updated 9 months ago
• Wang-ML-Lab / bayesian-peft
  Bayesian Low-Rank Adaptation of LLMs: BLoB [NeurIPS 2024] and TFB [NeurIPS 2025]
  ☆31Updated 3 months ago
• arumaekawa / DiLM
  Implementaiton of "DiLM: Distilling Dataset into Language Model for Text-level Dataset Distillation" (accepted by NAACL2024 Findings)".
  ☆26Updated 11 months ago
• tanganke / opcm
  official code repo for paper "Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging"
  ☆22Updated 3 months ago
• zepingyu0512 / in-context-mechanism
  code for EMNLP 2024 paper: How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for M…
  ☆13Updated last year
• TsinghuaC3I / SoRA
  [EMNLP 2023, Main Conference] Sparse Low-rank Adaptation of Pre-trained Language Models
  ☆84Updated last year
• PKU-ML / ContraNorm
  Official code for ICLR 2023 paper "ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond "
  ☆35Updated 2 years ago
• ExplainableML / sae-for-vlm
  [NeurIPS 2025] Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
  ☆60Updated last month
• khainb / EBSW
  Official PyTorch implementation for paper: Energy-Based Sliced Wasserstein Distance
  ☆19Updated 10 months ago
• hqsiswiliam / hira
  The repo for HiRA paper
  ☆36Updated last week
• ycjing / Awesome-Model-Merging
  A curated list of Model Merging methods.
  ☆95Updated last month
• fan23j / ICML2024-OT-CLIP
  Official Repository for ICML 2024 Paper "OT-CLIP: Understanding and Generalizing CLIP via Optimal Transport"
  ☆20Updated last month
• Nebularaid2000 / bottleneck
  PyTorch implementation of the paper "Discovering and Explaining the Representation Bottleneck of DNNs" (ICLR 2022 Oral)
  ☆37Updated last year
• ruthless-man / Awesome-Learn-from-Model
  Awesome Learn From Model Beyond Fine-Tuning: A Survey
  ☆80Updated last year
• IBM / model-reprogramming
  Repository for research works and resources related to model reprogramming <https://arxiv.org/abs/2202.10629>
  ☆64Updated 4 months ago
• lliai / Awesome-Low-Rank-Adaptation
  Awesome-Low-Rank-Adaptation
  ☆126Updated last year
• AntoAndGar / task_singular_vectors
  Task Singular Vectors: Reducing Task Interference in Model Merging. Merge models avoiding task interference through separable models.
  ☆47Updated last month