melisa-writer / short-transformersLinks
Prune transformer layers
☆69Updated last year
Alternatives and similar repositories for short-transformers
Users that are interested in short-transformers are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2024] Low rank memory efficient optimizer without SVD☆30Updated last month
- Code for studying the super weight in LLM☆115Updated 8 months ago
- The official implementation of the paper "What Matters in Transformers? Not All Attention is Needed".☆174Updated 4 months ago
- ☆199Updated 8 months ago
- ☆127Updated last year
- The official repo for "LLoCo: Learning Long Contexts Offline"☆118Updated last year
- Collection of autoregressive model implementation☆86Updated 3 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆61Updated 9 months ago
- Unofficial implementation of https://arxiv.org/pdf/2407.14679☆48Updated 11 months ago
- Code for Zero-Shot Tokenizer Transfer☆135Updated 6 months ago
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆198Updated last year
- code for training & evaluating Contextual Document Embedding models☆196Updated 2 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆82Updated 3 weeks ago
- ☆68Updated last year
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆324Updated 3 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆167Updated last year
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆151Updated 4 months ago
- Understand and test language model architectures on synthetic tasks.☆221Updated 3 weeks ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆140Updated last year
- BABILong is a benchmark for LLM evaluation using the needle-in-a-haystack approach.☆209Updated 3 months ago
- Repository for the Q-Filters method (https://arxiv.org/pdf/2503.02812)☆34Updated 5 months ago
- ☆190Updated 7 months ago
- Manage scalable open LLM inference endpoints in Slurm clusters☆268Updated last year
- ☆48Updated 11 months ago
- This is the official repository for Inheritune.☆112Updated 6 months ago
- ☆83Updated 6 months ago
- Set of scripts to finetune LLMs☆37Updated last year
- The evaluation framework for training-free sparse attention in LLMs☆88Updated last month
- Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)☆160Updated 3 months ago
- ☆51Updated 9 months ago