Alternatives and similar repositories for RepresentationSurgery:

Users that are interested in RepresentationSurgery are comparing it to the libraries listed below

• tanganke / peta
  Code for paper "Parameter Efficient Multi-task Model Fusion with Partial Linearization"
  ☆19Updated 5 months ago
• EnnengYang / AdaMerging
  AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.
  ☆67Updated 4 months ago
• nik-dim / tall_masks
  Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]
  ☆39Updated 4 months ago
• LZY-the-boys / Twin-Merging
  [NeurIPS2024] Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging
  ☆50Updated 3 months ago
• abhishekpanigrahi1996 / Skill-Localization-by-grafting
  ☆50Updated last year
• harveyhuang18 / EMR_Merging
  [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging
  ☆45Updated this week
• uiuctml / Localize-and-Stitch
  Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
  ☆23Updated last month
• yule-BUAA / MergeLLM
  Codes for Merging Large Language Models
  ☆29Updated 6 months ago
• keven980716 / weak-to-strong-deception
  [ICLR 2025] Code&Data for the paper "Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization"
  ☆12Updated 8 months ago
• sail-sg / Attention-Sink
  [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)
  ☆49Updated 4 months ago
• which47 / LLMCL
  Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning
  ☆29Updated 3 months ago
• adymaharana / d2pruning
  ☆32Updated last year
• Jiacheng-Zhu-AIML / AsymmetryLoRA
  Preprint: Asymmetry in Low-Rank Adapters of Foundation Models
  ☆35Updated last year
• UKPLab / iclr2024-model-merging
  This is the repository for "Model Merging by Uncertainty-Based Gradient Matching", ICLR 2024.
  ☆26Updated 9 months ago
• princeton-nlp / benign-data-breaks-safety
  ☆30Updated 5 months ago
• tanganke / weight-ensembling_MoE
  Code for paper "Merging Multi-Task Models via Weight-Ensembling Mixture of Experts"
  ☆19Updated 8 months ago
• VITA-Group / Junk_DNA_Hypothesis
  [ICML 2024] Junk DNA Hypothesis: A Task-Centric Angle of LLM Pre-trained Weights through Sparsity; Lu Yin*, Ajay Jaiswal*, Shiwei Liu, So…
  ☆16Updated 9 months ago
• circle-hit / SAPT
  Code for ACL 2024 accepted paper titled "SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language …
  ☆31Updated last month
• SempraETY / Pruning-via-Merging
  ☆17Updated 3 months ago
• yaojin17 / Unlearning_LLM
  [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"
  ☆52Updated 5 months ago
• git-disl / Lisa
  This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)
  ☆17Updated 5 months ago
• tmlr-group / NoisyRationales
  [NeurIPS 2024] "Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?"
  ☆33Updated last month
• JingXuTHU / Random-Masking-Finds-Winning-Tickets-for-Parameter-Efficient-Fine-tuning
  ☆13Updated 9 months ago
• BeyonderXX / TRACE
  TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models
  ☆64Updated last year
• GATECH-EIC / ACT
  [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…
  ☆31Updated 8 months ago
• swj0419 / muse_bench
  ☆19Updated 7 months ago
• gortizji / tangent_task_arithmetic
  Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".
  ☆95Updated last year
• THU-KEG / Skill-Neuron
  Source code for EMNLP2022 paper "Finding Skill Neurons in Pre-trained Transformers via Prompt Tuning".
  ☆18Updated last year
• git-disl / Vaccine
  This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)
  ☆39Updated 3 months ago
• hkust-nlp / PEM_composition
  [NeurIPS 2023] Github repository for "Composing Parameter-Efficient Modules with Arithmetic Operations"
  ☆60Updated last year