Francis LaBounty's repositories
Dreambooth-Anything
A repository to consolidate stable diffusion finetuning scripts. Train inpainting, depth, v1+, v2+, image variations, image colorization, whatever. Train with optimizations like 8 bit adam and xformers for faster and more memory efficient training.
ChatGPT-Desktop
ChatGPT desktop app made with PyQT5. Features include web search, prompt manager, wolfram alpha integration, pdf summarization and more!
stable-diffusion-webui
Stable Diffusion web UI - with text conditioning vector interpolations and disco style animations
audiolm-pytorch
Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
BentNormalsCPUModule
CPU python module for Blender 3D addon Bent Normals
BentNormalsCUDAModule
CUDA python module for Blender 3D addon Bent Normals
cublas-SGEMM-CUDA
cublas SGEMM implementation using the CUDA programming language. Asynchronous and serial versions provided. Sources: "Learn CUDA Programming" from Jaegeun Han and Bharatkumar Sharma.
dreambooth_depth2img
adaptation of huggingface's dreambooth training script to support depth2img
musiclm-pytorch
Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch
ANN-CUDA-Framework
Basic ANN Framework utilizing cudnn and the CUDA programming language. Sources: "Learn CUDA programming" from Jaegeun Han and Bharatkumar Sharma.
ANN-CUDA-Pybind11
Functional ANN framework utilizing cudnn and the CUDA programming language to create a python module. Sources: "Learn CUDA programming" from Jaegeun Han and Bharatkumar Sharma.
cddpo
Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"
FasterTransformer
Transformer related optimization, including BERT, GPT
generative-recommenders
Repository hosting code used to reproduce results in "Actions Speak Louder than Words Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).
LLaVA-RLHF-Agent
Aligning LMMs with Factually Augmented RLHF - Desktop agent
mobilestylegan-NFTs
MobileStyleGan NFTs using the ONNX Web Runtime
Parameter-Efficient-MoE
Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks
Radix-Sort-CUDA
One radix sort implementation demonstrating the use of warp level primitives and the other demonstrating the use of the thrust library. Sources: "Learn CUDA Programming" from Jaegeun Han and Bharatkumar Sharma.
Recursive-Quick-Sort-Cuda
Recursive quick sort implementation using the CUDA programming language. Sources: "Learn CUDA Programming" from Jaegeun Han and Bharatkumar Sharma.
self-rewarding-lm-pytorch
Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI
transformer-deploy
Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀
Vector-Pybind11-Module
Pybind11 module of a Vec3 class