nathanielyvo / WUDI-Merging
The official repository of "Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors""
☆14Updated last week
Alternatives and similar repositories for WUDI-Merging
Users that are interested in WUDI-Merging are comparing it to the libraries listed below
Sorting:
- Chain of Thoughts (CoT) is so hot! so long! We need short reasoning process!☆52Updated last month
- A versatile toolkit for applying Logit Lens to modern large language models (LLMs). Currently supports Llama-3.1-8B and Qwen-2.5-7B, enab…☆79Updated 2 months ago
- The official code repository for PRMBench.☆73Updated 2 months ago
- Awesome-Long2short-on-LRMs is a collection of state-of-the-art, novel, exciting long2short methods on large reasoning models. It contains…☆208Updated 2 weeks ago
- This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.☆79Updated this week
- Model merging is a highly efficient approach for long-to-short reasoning.☆46Updated last month
- Language Imbalance Driven Rewarding for Multilingual Self-improving☆17Updated 6 months ago
- Implementation code for ACL2024：Advancing Parameter Efficiency in Fine-tuning via Representation Editing☆14Updated last year
- ☆34Updated 2 months ago
- TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆138Updated 2 months ago
- ☆59Updated last month
- ☆95Updated 3 weeks ago
- a survey of long-context LLMs from four perspectives, architecture, infrastructure, training, and evaluation☆46Updated last month
- ☆33Updated 5 months ago
- ☆32Updated 7 months ago
- The reinforcement learning codes for dataset SPA-VL☆32Updated 10 months ago
- FeatureAlignment = Alignment + Mechanistic Interpretability☆28Updated 2 months ago
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨☆211Updated last year
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆67Updated 3 months ago
- 📜 Paper list on decoding methods for LLMs and LVLMs☆43Updated 2 weeks ago
- [ICLR 2025] Code and Data Repo for Paper "Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation"☆46Updated 4 months ago
- Repository for Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning☆162Updated last year
- Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".☆52Updated 5 months ago
- The OlymMATH dataset☆11Updated 3 weeks ago
- AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models, ICLR 2025 (Outstanding Paper)☆214Updated 2 weeks ago
- 🔥 How to efficiently and effectively compress the CoTs or directly generate concise CoTs during inference while maintaining the reasonin…☆41Updated 2 weeks ago
- 😎 A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond☆208Updated this week
- [EMNLP 2024 Findings🔥] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context In…☆93Updated 6 months ago
- [ACL 2024] The official codebase for the paper "Self-Distillation Bridges Distribution Gap in Language Model Fine-tuning".☆119Updated 6 months ago
- ☆26Updated 6 months ago