KaihuaTang / Qwen-Tokenizer-PrunerLinks
Due to the huge vocaburary size (151,936) of Qwen models, the Embedding and LM Head weights are excessively heavy. Therefore, this project provides a Tokenizer vocabulary shearing solution for Qwen and Qwen-VL.
☆23Updated 11 months ago
Alternatives and similar repositories for Qwen-Tokenizer-Pruner
Users that are interested in Qwen-Tokenizer-Pruner are comparing it to the libraries listed below
Sorting:
- ☆110Updated last month
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆48Updated 8 months ago
- Multi-Candidate Speculative Decoding☆35Updated last year
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆52Updated 4 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆167Updated last year
- [AAAI 2024] Fluctuation-based Adaptive Structured Pruning for Large Language Models☆56Updated last year
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆194Updated 5 months ago
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆94Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆93Updated 3 months ago
- ☆23Updated last month
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆135Updated last year
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆28Updated 5 months ago
- TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆166Updated 3 weeks ago
- qwen-nsa☆68Updated 3 months ago
- Repository of LV-Eval Benchmark☆67Updated 10 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆59Updated last year
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]☆41Updated this week
- Efficient Mixture of Experts for LLM Paper List☆82Updated 7 months ago
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆86Updated 3 weeks ago
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆38Updated last year
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆107Updated 3 months ago
- ☆64Updated 7 months ago
- Unofficial implementations of block/layer-wise pruning methods for LLMs.☆72Updated last year
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆84Updated 3 weeks ago
- Inference Code for Paper "Harder Tasks Need More Experts: Dynamic Routing in MoE Models"☆56Updated 11 months ago
- [ACL 2024] Official PyTorch implementation of "IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact"☆44Updated last year
- 🚀 LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training☆86Updated 7 months ago
- Model merging is a highly efficient approach for long-to-short reasoning.☆73Updated last month
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆71Updated 4 months ago
- Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models☆45Updated 8 months ago