Vikash Sehwag's starred repositories
PrettyErrors
Prettify Python exception output to make it legible.
InternLM-XComposer
InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output
consistencydecoder
Consistency Distilled Diff VAE
Lumina-T2X
Lumina-T2X is a unified framework for Text to Any Modality Generation
calculate-flops.pytorch
The calflops is designed to calculate FLOPs、MACs and Parameters in all various neural networks, such as Linear、 CNN、 RNN、 GCN、Transformer(Bert、LlaMA etc Large Language Model)
UltraPixel
Implementation of UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks
llm-strategy
Directly Connecting Python to LLMs via Strongly-Typed Functions, Dataclasses, Interfaces & Generic Types
soft-moe-pytorch
Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch
jailbreakbench
An Open Robustness Benchmark for Jailbreaking Language Models [arXiv 2024]
cifar10-airbench
94% on CIFAR-10 in 3.09 seconds 💨 96% in 27 seconds
MosaicFusion
[IJCV 2024] MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation
llama-inference
experiments with inference on llama
pytorch-benchmark
Easily benchmark PyTorch model FLOPs, latency, throughput, allocated gpu memory and energy consumption
fast-differential-privacy
Fast, memory-efficient, scalable optimization of deep learning with differential privacy