MrGGLS / BlockPruner
A block pruning framework for LLMs.
☆21Updated 9 months ago
Alternatives and similar repositories for BlockPruner:
Users that are interested in BlockPruner are comparing it to the libraries listed below
- ☆17Updated 4 months ago
- TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆103Updated 3 weeks ago
- Official implementation for LaCo (EMNLP 2024 Findings)☆16Updated 6 months ago
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆53Updated last month
- Official Pytorch Implementation of Our Paper Accepted at ICLR 2024-- Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLM…☆45Updated 11 months ago
- ☆48Updated 3 months ago
- ☆31Updated last year
- ☆50Updated last year
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆56Updated last month
- [ICLR 2025] The official pytorch implement of "Dynamic Low-Rank Sparse Adaptation for Large Language Models".☆13Updated 2 weeks ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆33Updated 9 months ago
- Code for "ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models" (ICLR 2024)☆19Updated last year
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆45Updated last month
- AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.☆72Updated 5 months ago
- [ICML'24 Oral] APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference☆33Updated 9 months ago
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆77Updated 9 months ago
- Official code for our paper, "LoRA-Pro: Are Low-Rank Adapters Properly Optimized? "☆108Updated 3 weeks ago
- DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling☆29Updated 8 months ago
- Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]☆42Updated 5 months ago
- Official implementation of the ICLR paper "Streamlining Redundant Layers to Compress Large Language Models"☆14Updated 3 weeks ago
- ☆82Updated 2 weeks ago
- ☆20Updated 10 months ago
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆52Updated last week
- LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning☆29Updated 11 months ago
- Representation Surgery for Multi-Task Model Merging. ICML, 2024.☆42Updated 5 months ago
- A curated list of Model Merging methods.☆91Updated 6 months ago
- Less is More: Task-aware Layer-wise Distillation for Language Model Compression (ICML2023)☆34Updated last year
- Unofficial implementations of block/layer-wise pruning methods for LLMs.☆66Updated 11 months ago
- ☆39Updated 4 months ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆57Updated 6 months ago