lliai
Follow
-
D2MoE Public
D^2-MoE: Delta Decompression for MoE-based LLMs Compression
-
Paper survey of efficient computation for large scale models.
-
DSA Public
Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models
Python UpdatedOct 29, 2024 -
-
Auto-DAS Public
[ECCV2024] Auto-DAS: Automated Proxy Discovery for Training-free Distillation-aware Architecture Search
-
Auto-GAS Public
[ECCV2024] Auto-GAS: Automated Proxy Discovery for Training-free Generative Architecture Search
-
VLoRA Public
Forked from FeipengMa6/VLoRA[NeurIPS 2024] Visual Perception by Large Language Model’s Weights
Python Apache License 2.0 UpdatedOct 17, 2024 -
-
OLMoE Public
Forked from allenai/OLMoEOLMoE: Open Mixture-of-Experts Language Models
Jupyter Notebook Apache License 2.0 UpdatedSep 4, 2024 -
Awesome-LLM-Synthetic-Data Public
Forked from wasiahmad/Awesome-LLM-Synthetic-DataA reading list on LLM based Synthetic Data Generation 🔥
MIT License UpdatedAug 12, 2024 -
SANE Public
Forked from HSG-AIML/SANECode Repository for the ICML 2024 paper: "Towards Scalable and Versatile Weight Space Learning".
Python UpdatedJul 11, 2024 -
DetKDS Public
[ICML2024] DetKDS: Knowledge Distillation Search for Object Detectors
-
AttnZero Public
[ECCV2024] AttnZero: Efficient Attention Discovery for Vision Transformers
-
moe-quantization Public
Forked from UNITES-Lab/moe-quantizationOfficial code for the paper "Examining Post-Training Quantization for Mixture-of-Experts: A Benchmark"
Python MIT License UpdatedJun 26, 2024 -
LGD Public
Forked from mZhenz/LGDLightweight Model Pre-training via Language Guided Knowledge Distillation
Jupyter Notebook UpdatedJun 24, 2024 -
MATES Public
Forked from cxcscmu/MATESOfficial repository for MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models
Python MIT License UpdatedJun 13, 2024 -
DiscoPOP Public
Forked from luchris429/DiscoPOPCode for Discovering Preference Optimization Algorithms with and for Large Language Models
Python MIT License UpdatedJun 13, 2024 -
-
SimDA Public
Forked from ChenHsing/SimDA[CVPR 2024] SimDA: Simple Diffusion Adapter for Efficient Video Generation
Python UpdatedMay 7, 2024 -
Awesome Knowledge-Distillation for CV
-
-
-
loretta Public
Forked from yifanycc/loretta[NAACL 24] LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models
Python GNU General Public License v3.0 UpdatedApr 19, 2024 -
AdaGP Public
Forked from BaiTheBest/SparseLLMOfficial Repo for Adaptive Global Pruning of LLMs
Python Apache License 2.0 UpdatedApr 15, 2024 -
Awesome-Efficient-LLM Public
Forked from horseee/Awesome-Efficient-LLMA curated list for Efficient Large Language Models
Python UpdatedApr 10, 2024 -
T-GATE Public
Forked from HaozheLiu-ST/T-GATEAccelerating Text-to-Image Diffusion Model for Free
Python MIT License UpdatedApr 4, 2024 -
shortened-llm Public
Forked from Nota-NetsPresso/shortened-llmCompressed LLMs for Efficient Text Generation [ICLR'24 Workshop]
Python UpdatedApr 3, 2024 -
zigma Public
Forked from CompVis/zigmaThe official implementation of "ZigMa: A DiT-Style Mamba-based Diffusion Model
Python Apache License 2.0 UpdatedApr 2, 2024 -
TFMQ-DM Public
Forked from ModelTC/TFMQ-DM[CVPR 2024] TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models
Jupyter Notebook Apache License 2.0 UpdatedMar 31, 2024 -
APQ-DM Public
Forked from ChangyuanWang17/APQ-DMThis is the official pytorch implementation for the paper: Towards Accurate Post-training Quantization for Diffusion Models.(CVPR24)
Python Apache License 2.0 UpdatedMar 27, 2024