dibu28

llama3

The official Meta Llama 3 GitHub site

llama-cpp-python

Python bindings for llama.cpp

argilla

Argilla is a collaboration platform for AI engineers and domain experts that require high-quality outputs, full data ownership, and overall efficiency.

t-few

Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"

TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

talk-llama-fast

Port of OpenAI's Whisper model in C/C++ with xtts and wav2lip

text_generation_webui_xtt_Alts

XTTSv2 Extension for oobabooga text-generation-webui

text_generation_webui_xtts

XTTSv2 Extension for oobabooga text-generation-webui

JellyBoxPlayer

Native desktop and mobile client for Jellyfin

DnsServer

Technitium DNS Server

AdGuardHome

Network-wide ads & trackers blocking DNS server

eidolon

An Open Source Agent Service Framework

fabric

fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

Real-SR

Real-World Super-Resolution via Kernel Estimation and Noise Injection

deblur-gan

Keras implementation of "DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks"

DeblurGAN

Image Deblurring using Generative Adversarial Networks

TextZoom

A super-resolution dataset of paired LR-HR scene text images

RealSR

Real-World Super-Resolution via Kernel Estimation and Noise Injection

Blind-Deblurring

Blind Deblurring (Deconvolution) System

Image_Denoising_with_ROF_algorithm

The total variation denoising method, proposed by Rudin, Osher and Fatermi, circa 1992, is a PDE-based algorithm for edge-preserving noise removal. The ROF denoising algorithm is based on the partial differential of total variation of an image such that by finding a good appoximation of the local minima of the PD of the total variation value we can find that the total noise in the image will also be in a local minima. Unlike a conventional low-pass filter, TV denoising is defined in terms of an optimization problem. In effect the output of the TV denoising 'filter' is obtained by minimizing a particular bounded cost function. Total variation itself is a measure of the complexity of an image with respect to its spatial variation, usually an integral of the greyscale gradient across the rectangular image domain.

python

Awesome-LLM-RAG

Awesome-LLM-RAG: a curated list of advanced retrieval augmented generation (RAG) in Large Language Models

brisque

Blind/Referenceless Image Spatial QUality Evaluator (BRISQUE)

fast-reflection-removal

Removes reflections quickly and easily.

Fewshot-Learning-with-BERT

We attempt to do few shot learning with BERT and prototypical network for Intent classification

segtok

Segtok v2 is here: https://github.com/fnl/syntok -- A rule-based sentence segmenter (splitter) and a word tokenizer using orthographic features.

syntok

Text tokenization and sentence segmentation (segtok v2)

few-shot-text-classification

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

OMRChecker

Evaluate OMR sheets fast and accurately using a scanner 🖨 or your phone 🤳.