CASE-Lab-UMD / LLM-Drop
The official implementation of the paper "What Matters in Transformers? Not All Attention is Needed".
☆143Updated last week
Related projects ⓘ
Alternatives and complementary repositories for LLM-Drop
- ☆199Updated 5 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆135Updated 5 months ago
- Repo for Rho-1: Token-level Data Selection & Selective Pretraining of LLMs.☆307Updated 7 months ago
- Official PyTorch implementation of DistiLLM: Towards Streamlined Distillation for Large Language Models (ICML 2024)☆139Updated 2 months ago
- ☆153Updated 9 months ago
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆129Updated 2 months ago
- ☆122Updated 10 months ago
- LLM-Merging: Building LLMs Efficiently through Merging☆176Updated last month
- ☆90Updated 4 months ago
- Official implementation of "DoRA: Weight-Decomposed Low-Rank Adaptation"☆122Updated 6 months ago
- The official repo for "LLoCo: Learning Long Contexts Offline"☆113Updated 5 months ago
- ☆64Updated last month
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)☆199Updated 6 months ago
- Prune transformer layers☆65Updated 5 months ago
- Code accompanying the paper "Massive Activations in Large Language Models"☆123Updated 8 months ago
- Understand and test language model architectures on synthetic tasks.☆163Updated 6 months ago
- Implementation of CALM from the paper "LLM Augmented LLMs: Expanding Capabilities through Composition", out of Google Deepmind☆169Updated 2 months ago
- Explorations into some recent techniques surrounding speculative decoding☆212Updated last year
- open-source code for paper: Retrieval Head Mechanistically Explains Long-Context Factuality☆160Updated 3 months ago
- ☆175Updated this week
- ☆247Updated last year
- ☆184Updated last month
- Unofficial Implementation of Evolutionary Model Merging☆33Updated 7 months ago
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆64Updated 5 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆214Updated this week
- A family of compressed models obtained via pruning and knowledge distillation☆285Updated last week
- The official evaluation suite and dynamic data release for MixEval.☆224Updated 2 weeks ago
- ☆115Updated 4 months ago
- Benchmarking LLMs with Challenging Tasks from Real Users☆198Updated 3 weeks ago
- The official implementation of the paper "Demystifying the Compression of Mixture-of-Experts Through a Unified Framework".☆48Updated 3 weeks ago