talha_yousuf's repositories
diffusers
š¤ Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
Google-Image-Scraper
A library to scrap google images
lightning-tutorials
Collection of Pytorch lightning tutorial form as rich scripts automatically transformed to ipython notebooks.
LLM_finetune
synthetic dataset gneration and fine tune
MIRNetv2
[TPAMI 2022] Learning Enriched Features for Fast Image Restoration and Enhancement. Results on Defocus Deblurring, Denoising, Super-resolution, and image enhancement
multilingual_kws
Few-shot Keyword Spotting in Any Language and Multilingual Spoken Word Corpus
pl-hydra-cloth-segmentation-triton
Cloth Segmentation model scalable deployment using nvidia-triton
python_backend
Triton backend that enables pre-process, post-processing and other logic to be implemented in Python.
quesiton-answer-model
question answering model fine tuning
stable-diffusion-BLS
Deploy stable diffusion model with onnx/tenorrt + tritonserver
stable-diffusion-webui
Stable Diffusion web UI
TensorRT
NVIDIAĀ® TensorRTā¢, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for inference applications.
tensorrt-SD-plugins
this repo. enlists pre-built tensorrt plugins libraries
text-generation-webui
A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA.
transformer_pose
given a model giving pose in form of 128 points, find if person falls or not using a transformer based model
Trition-Tutorials
This repository contains tutorials and examples for Triton Inference Server
viton_dataset_huggingface_format
convert the viton dataset into huggingface fomat, it will give train/test splits and pairted/unpaired support
vllm-multimodal
make vllm accept multi modal
yolov5-face
YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)
Yolov5-ONNX
ONNX Implementation of Yolov5
yolov5-original
YOLOv5 š in PyTorch > ONNX > CoreML > TFLite