Pinned Repositories
LLaMA2-Accessory
An Open-source Toolkit for LLM Development
BEVFormer
This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.
BiPointNet
This project is the official implementation of our accepted ICLR 2021 paper BiPointNet: Binary Neural Network for Point Clouds.
bottleneck-transformer-pytorch
Implementation of Bottleneck Transformer - Pytorch
coco2pascal2txt
Convert annotations of COCO format to Pascal VOC format to Yolo Darknet format
detr
End-to-End Object Detection with Transformers
HAWQ
Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.
LLaMA2-Accessory
An Open-source Toolkit for LLM Development
llama_finetuning
LLaMA 大模型 finetuning
NoisyQuant
An official implement of CVPR 2023 paper - NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers
kriskrisliu's Repositories
kriskrisliu/NoisyQuant
An official implement of CVPR 2023 paper - NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers
kriskrisliu/coco2pascal2txt
Convert annotations of COCO format to Pascal VOC format to Yolo Darknet format
kriskrisliu/LLaMA2-Accessory
An Open-source Toolkit for LLM Development
kriskrisliu/llama_finetuning
LLaMA 大模型 finetuning
kriskrisliu/BEVFormer
This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.
kriskrisliu/BiPointNet
This project is the official implementation of our accepted ICLR 2021 paper BiPointNet: Binary Neural Network for Point Clouds.
kriskrisliu/bottleneck-transformer-pytorch
Implementation of Bottleneck Transformer - Pytorch
kriskrisliu/detr
End-to-End Object Detection with Transformers
kriskrisliu/detr3d
kriskrisliu/HAWQ
Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.
kriskrisliu/llama
Inference code for LLaMA models
kriskrisliu/EfficientLLM
kriskrisliu/llama-1
User-friendly LLaMA: Train or Run the model using PyTorch. Nothing else.
kriskrisliu/LLaMA-Adapter
LLaMA-Adapter: Tuning LLaMA within One Hour and 8M Parameters
kriskrisliu/mmdetection3d
OpenMMLab's next-generation platform for general 3D object detection.
kriskrisliu/MMLLaMA2
kriskrisliu/PETR
PETR: Position Embedding Transformation for Multi-View 3D Object Detection
kriskrisliu/PTQ4ViT_noisy
Post-Training Quantization for Vision transformers.
kriskrisliu/PyHessian
PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks
kriskrisliu/PyTorch-ONNX-TFLite
kriskrisliu/pytorch-yolov3-quantization
kriskrisliu/q-diffusion
[ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.
kriskrisliu/Quant_timm
quantization of PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
kriskrisliu/ReCU
Pytorch implementation of our paper accepted by ICCV 2021 -- ReCU: Reviving the Dead Weights in Binary Neural Networks http://arxiv.org/abs/2103.12369
kriskrisliu/stanford_alpaca
kriskrisliu/TencentPretrain
Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo
kriskrisliu/vision
Datasets, Transforms and Models specific to Computer Vision
kriskrisliu/yolov3-quantization
kriskrisliu/yolov5-relu