Edenzzzz's repositories
Stable-Diffusion-for-book-cover-generation
Code runs on GPU with 12 GB memory. Fine-tuning Stable Diffusion on Goodread's best books dataset to test the model's transfer learning ability.
Stable-Diffusion-Compositions-Analysis
Stable Diffusion Compositions Analysis
Attend-and-Excite
Official Implementation for "Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models" (SIGGRAPH 2023)
bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.
butterfly
Butterfly matrix multiplication in PyTorch
ColossalAI
Making large AI models cheaper, faster and more accessible
ControlNet_attn_map
Let us control diffusion models!
DETA
Detection Transformers with Assignment
keras
Deep Learning for humans
LoRA
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
m2
Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"
Megatron-LM
Ongoing research training transformer models at scale
MLSys-Intro
Tests to get started on MLSys
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
nccl-tests
NCCL Tests
NeSVoR
NeSVoR is a package for GPU-accelerated slice-to-volume reconstruction.
ocnn-pytorch
Octree-based Sparse Convolutional Neural Networks
Partial_Distance_Correlation
This is the official GitHub for paper: On the Versatile Uses of Partial Distance Correlation in Deep Learning, in ECCV 2022
peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
pyreft
ReFT: Representation Finetuning for Language Models
qlora
QLoRA: Efficient Finetuning of Quantized LLMs
ring-flash-attention
Ring attention implementation with flash attention
torch_fsdp_example
A usage example showing the benefit FSDP(ZeRO3) over default DDP.
TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.