OpenSparseLLMs / LLaMA-MoE-v2Links
π LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training
β89Updated 10 months ago
Alternatives and similar repositories for LLaMA-MoE-v2
Users that are interested in LLaMA-MoE-v2 are comparing it to the libraries listed below
Sorting:
- CoT-Valve: Length-Compressible Chain-of-Thought Tuningβ86Updated 7 months ago
- [EMNLP 2024 Findingsπ₯] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inβ¦β102Updated 11 months ago
- β101Updated 3 weeks ago
- Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shapingβ54Updated 4 months ago
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMsβ182Updated 3 months ago
- [ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Modelsβ136Updated 3 months ago
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoningβ69Updated 2 months ago
- Open-Pandora: On-the-fly Control Video Generationβ34Updated 10 months ago
- Model merging is a highly efficient approach for long-to-short reasoning.β84Updated 4 months ago
- β46Updated 6 months ago
- β155Updated 4 months ago
- β117Updated last year
- [ACL' 25] The official code repository for PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models.β81Updated 7 months ago
- β169Updated 4 months ago
- β129Updated 6 months ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibratiβ¦β44Updated last year
- This repo contains evaluation code for the paper "MileBench: Benchmarking MLLMs in Long Context"β35Updated last year
- β119Updated 4 months ago
- β133Updated 3 weeks ago
- β28Updated last year
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*β109Updated 4 months ago
- [NeurIPS 2025] Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chainsβ54Updated 2 months ago
- [ICML'25] Official code of paper "Fast Large Language Model Collaborative Decoding via Speculation"β28Updated 3 months ago
- Inference Code for Paper "Harder Tasks Need More Experts: Dynamic Routing in MoE Models"β63Updated last year
- [TMLR 2025] Efficient Reasoning Models: A Surveyβ265Updated last week
- β159Updated last year
- "what, how, where, and how well? a survey on test-time scaling in large language models" repositoryβ70Updated this week
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concenβ¦β80Updated 3 months ago
- β43Updated last week
- Large Language Models Can Self-Improve in Long-context Reasoningβ73Updated 10 months ago