CASE-Lab-UMD / LLM-DropLinks
The official implementation of the paper "What Matters in Transformers? Not All Attention is Needed".
☆173Updated 2 months ago
Alternatives and similar repositories for LLM-Drop
Users that are interested in LLM-Drop are comparing it to the libraries listed below
Sorting:
- ☆197Updated 6 months ago
- ☆222Updated 11 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆161Updated 11 months ago
- Official PyTorch implementation of DistiLLM: Towards Streamlined Distillation for Large Language Models (ICML 2024)☆217Updated 2 months ago
- Explorations into some recent techniques surrounding speculative decoding☆268Updated 5 months ago
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆301Updated last month
- Code for studying the super weight in LLM☆104Updated 6 months ago
- Code accompanying the paper "Massive Activations in Large Language Models"☆162Updated last year
- Official implementation of "DoRA: Weight-Decomposed Low-Rank Adaptation"☆123Updated last year
- ☆125Updated last year
- Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)☆156Updated last month
- The official repo for "LLoCo: Learning Long Contexts Offline"☆116Updated 11 months ago
- ☆179Updated last year
- LLM-Merging: Building LLMs Efficiently through Merging☆197Updated 8 months ago
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆70Updated 2 months ago
- open-source code for paper: Retrieval Head Mechanistically Explains Long-Context Factuality☆195Updated 10 months ago
- ☆259Updated last year
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆143Updated 8 months ago
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆84Updated 11 months ago
- Repo for Rho-1: Token-level Data Selection & Selective Pretraining of LLMs.☆417Updated last year
- ☆79Updated 4 months ago
- minimal GRPO implementation from scratch☆90Updated 2 months ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆134Updated 9 months ago
- ☆248Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆167Updated last month
- LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.☆228Updated 9 months ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆60Updated 8 months ago
- Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind☆96Updated last year
- A family of compressed models obtained via pruning and knowledge distillation☆342Updated 6 months ago
- Official Implementation of SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks☆37Updated 4 months ago