SempraETY / Pruning-via-Merging
☆18Updated 4 months ago
Alternatives and similar repositories for Pruning-via-Merging:
Users that are interested in Pruning-via-Merging are comparing it to the libraries listed below
- A block pruning framework for LLMs.☆22Updated 9 months ago
- [ICLR 2025] The official pytorch implement of "Dynamic Low-Rank Sparse Adaptation for Large Language Models".☆14Updated last month
- Official Pytorch Implementation of Our Paper Accepted at ICLR 2024-- Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLM…☆46Updated last year
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆36Updated 9 months ago
- Official implementation for LaCo (EMNLP 2024 Findings)☆16Updated 6 months ago
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆56Updated last month
- [ICML'24 Oral] APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference☆37Updated 10 months ago
- To mitigate position bias in LLMs, especially in long-context scenarios, we scale only one dimension of LLMs, reducing position bias and …☆11Updated 9 months ago
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆53Updated 3 weeks ago
- LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning☆30Updated last year
- Code for "ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models" (ICLR 2024)☆19Updated last year
- TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆120Updated last month
- Official Implementation of SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks☆36Updated 2 months ago
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆62Updated 2 months ago
- ☆15Updated 5 months ago
- ☆11Updated 6 months ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆61Updated 5 months ago
- ☆50Updated last year
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆79Updated 10 months ago
- Model merging is a highly efficient approach for long-to-short reasoning.☆38Updated 3 weeks ago
- Official implementation of the ICLR paper "Streamlining Redundant Layers to Compress Large Language Models"☆19Updated last week
- ☆16Updated this week
- ☆48Updated 4 months ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆45Updated last month
- Code for paper "Parameter Efficient Multi-task Model Fusion with Partial Linearization"☆21Updated 7 months ago
- Codes for Merging Large Language Models☆29Updated 8 months ago
- DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling☆29Updated 9 months ago
- ☆31Updated last year
- [ICLR 2025] The official pytorch implement of "Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Cont…☆28Updated 4 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆36Updated 8 months ago