Zefan-Cai / PyramidKV
The Official Implementation of PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
☆480Updated last month
Related projects: ⓘ
- The framework to prune LLMs to any size and any config.☆96Updated 6 months ago
- The Official Repo of ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code (https://a…☆350Updated last week
- Multilingual Corpus of Web Fiction☆211Updated 2 months ago
- Benchmarking LLMs via Uncertainty Quantification☆206Updated 7 months ago
- Code Efficiency Benchmark☆81Updated last month
- Awesome LLMs on Device: A Comprehensive Survey☆613Updated this week
- Code for paper "GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators"☆192Updated last month
- ☆366Updated 3 weeks ago
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆203Updated 2 weeks ago
- Matryoshka Query Transformer for Large Vision-Language Models☆88Updated 2 months ago
- 使用deepspeed从头开始训练一个LLM,经过pretrain和sft阶段,验证llm学习知识、理解语言、回答问题的能力☆145Updated 2 months ago
- ☆353Updated last month
- We leverage 14 datasets as OOD test data and conduct evaluations on 8 NLU tasks over 21 popularly used models. Our findings confirm that …☆115Updated last year
- [ACL 2024] User-friendly evaluation framework: Eval Suite & Benchmarks: UHGEval, HaluEval, HalluQA☆176Updated 2 weeks ago
- [NeurIPS 2022] Official Code for REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering☆132Updated this week
- (AAAI 2024) BLIVA: A Simple Multimodal LLM for Better Handling of Text-rich Visual Questions☆260Updated 5 months ago
- Unofficial Implementation of ReplaceAnything: https://aigcdesigngroup.github.io/replace-anything/☆526Updated 3 months ago
- Accelerate your Stable Diffusion inference with the library's universal C/C++ framework design, powered by ONNXRuntime & across platforms…☆610Updated last month
- ☆189Updated 2 months ago
- DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Models☆92Updated last week
- Evaluating dynamics capability of T2V generation models with DEVIL protocols.☆321Updated 3 weeks ago
- An MBTI Exploration of Large Language Models☆448Updated 7 months ago
- [ECCV 2024] Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?☆133Updated 2 weeks ago
- Large-Scale Selfie Video Dataset (L-SVD): A Benchmark for Emotion Recognition☆407Updated last month
- The official implementation of Self-Play Preference Optimization (SPPO)☆461Updated last month
- 动手构建一个完整的神经网络; Hands-on construction of a complete neural network☆13Updated last year
- AvaTaR: Optimizing LLM Agents for Tool-Assisted Knowledge Retrieval (https://arxiv.org/abs/2406.11200)☆140Updated last month
- The codes about "Uni-MoE: Scaling Unified Multimodal Models with Mixture of Experts"☆754Updated last week
- An official implementation of ShareGPT4Video: Improving Video Understanding and Generation with Better Captions☆1,220Updated last month
- Real-time and accurate open-vocabulary end-to-end object detection☆1,483Updated 2 weeks ago