Alternatives and similar repositories for subspace_fusion:

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

• swj0419 / muse_bench
  ☆19Updated 6 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)
  ☆15Updated 4 months ago
• EnnengYang / AdaMerging
  AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.
  ☆62Updated 3 months ago
• git-disl / Vaccine
  This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)
  ☆33Updated 2 months ago
• Vaidehi99 / InfoDeletionAttacks
  ☆40Updated last year
• licong-lin / negative-preference-optimization
  ☆45Updated 6 months ago
• git-disl / Booster
  This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturba…
  ☆13Updated 3 weeks ago
• princeton-nlp / benign-data-breaks-safety
  ☆26Updated 3 months ago
• OPTML-Group / SOUL
  Official repo for EMNLP'24 paper "SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning"
  ☆17Updated 3 months ago
• nik-dim / tall_masks
  Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]
  ☆39Updated 3 months ago
• Jayfeather1024 / Backdoor-Enhanced-Alignment
  ☆15Updated last month
• yaojin17 / Unlearning_LLM
  [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"
  ☆53Updated 4 months ago
• uiuctml / Localize-and-Stitch
  Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
  ☆22Updated 2 weeks ago
• tanganke / peta
  Code for paper "Parameter Efficient Multi-task Model Fusion with Partial Linearization"
  ☆17Updated 4 months ago
• Unispac / shallow-vs-deep-alignment
  Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep
  ☆65Updated 6 months ago
• vfleaking / PTST
  Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"
  ☆17Updated 10 months ago
• sail-sg / I-FSJ
  Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)
  ☆53Updated 2 weeks ago
• OPTML-Group / Unlearn-Sparse
  [NeurIPS23 (Spotlight)] "Model Sparsity Can Simplify Machine Unlearning" by Jinghan Jia*, Jiancheng Liu*, Parikshit Ram, Yuguang Yao, Gao…
  ☆67Updated 10 months ago
• ThuCCSLab / MergeGuard
  [CCS-LAMPS'24] LLM IP Protection Against Model Merging
  ☆11Updated 3 months ago
• facebookresearch / jailbreak-objectives
  Code and data to go with the Zhu et al. paper "An Objective for Nuanced LLM Jailbreaks"
  ☆22Updated last month
• locuslab / acr-memorization
  ☆30Updated last month
• decoding-comp-trust / comp-trust
  Codebase for decoding compressed trust.
  ☆22Updated 8 months ago
• ethz-spylab / rlhf-poisoning
  Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"
  ☆46Updated 9 months ago
• boyiwei / alignment-attribution-code
  Official Code for Paper: Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
  ☆68Updated 3 months ago
• mireshghallah / neighborhood-curvature-mia
  ☆21Updated last year
• EnnengYang / RepresentationSurgery
  Representation Surgery for Multi-Task Model Merging. ICML, 2024.
  ☆34Updated 3 months ago
• MartinPawel / In-Context-Unlearning
  "In-Context Unlearning: Language Models as Few Shot Unlearners". Martin Pawelczyk, Seth Neel* and Himabindu Lakkaraju*; ICML 2024.
  ☆21Updated last year
• srzer / MOD
  Official code for "Decoding-Time Language Model Alignment with Multiple Objectives".
  ☆18Updated 2 months ago
• OPTML-Group / Unlearn-WorstCase
  [ECCV24] "Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning" by Chongyu Fan*, Jiancheng Liu*, Alfred Hero, …
  ☆19Updated 3 months ago
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆88Updated 8 months ago