SungBalance

adaptdl

Resource-adaptive cluster scheduler for deep learning training.

AI-Shorts-Creator

AI-Video-Cropper is a Python-based tool that leverages the power of GPT-4 (OpenAI's language model) to automatically analyze videos, extract the most interesting sections, and crop them for improved viewing experience. This project combines the capabilities of GPT-4, FFmpeg, and OpenCV to automate the process of identifying highlights in videos

aiffel

aiomonitor

aiomonitor is module that adds monitor and python REPL capabilities for asyncio application

AjouStock

Stock trading project using Tensorflow(or Keras) with Python

albert

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

Algorithm

solution of algorithm problems

ao

torchao: PyTorch Architecture Optimization (AO). Performant kernels that work with PyTorch.

backgroundremover

BackgroundRemover lets you Remove Background from images and video with a simple command line interface

bert

TensorFlow code and pre-trained models for BERT

SungBalance/adaptdl

Resource-adaptive cluster scheduler for deep learning training.

SungBalance/AI-Shorts-Creator

AI-Video-Cropper is a Python-based tool that leverages the power of GPT-4 (OpenAI's language model) to automatically analyze videos, extract the most interesting sections, and crop them for improved viewing experience. This project combines the capabilities of GPT-4, FFmpeg, and OpenCV to automate the process of identifying highlights in videos

SungBalance/aiomonitor

aiomonitor is module that adds monitor and python REPL capabilities for asyncio application

SungBalance/ao

torchao: PyTorch Architecture Optimization (AO). Performant kernels that work with PyTorch.

SungBalance/backgroundremover

BackgroundRemover lets you Remove Background from images and video with a simple command line interface

SungBalance/bert

TensorFlow code and pre-trained models for BERT

SungBalance/byteps

A high performance and generic framework for distributed DNN training

SungBalance/Deep-Learning-Paper-Review-and-Practice

꼼꼼한 딥러닝 논문 리뷰와 코드 실습

SungBalance/graph_def_editor

GraphDef Editor: A port of the TensorFlow contrib.graph_editor package that operates over serialized graphs

SungBalance/ignite

High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

SungBalance/langchain-kr

LangChain 공식 Document, Cookbook, 그 밖의 실용 예제를 바탕으로 작성한 한국어 튜토리얼입니다. 본 튜토리얼을 통해 LangChain을 더 쉽고 효과적으로 사용하는 방법을 배울 수 있습니다.

SungBalance/llama.cpp

Port of Facebook's LLaMA model in C/C++

SungBalance/llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

SungBalance/LLM-Inference-tests

LLM-Inference-tests

SungBalance/LLM-Pruner

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support LLaMA, Llama-2, BLOOM, Vicuna, Baichuan, etc.

SungBalance/Megatron-LM

Ongoing research training transformer language models at scale, including: BERT & GPT-2

SungBalance/mergekit

Tools for merging pretrained large language models.

SungBalance/neodgm

Modern TrueType font based on an old-but-good Korean bitmap font.

SungBalance/PowerInfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

SungBalance/pyreft

ReFT: Representation Finetuning for Language Models

SungBalance/pytorch-Grid-Cells

SungBalance/regression-transformer

Regression Transformer (2023; Nature Machine Intelligence)

SungBalance/similar-patents-kobert

A Model that search similar Korean patents using KoBERT

SungBalance/stanford-dialogues

This codebase provides a unified interface to several dialogue datasets

SungBalance/Stock-Prediction-Models

Gathers machine learning and deep learning models for Stock forecasting including trading bots and simulations

SungBalance/stonkgs

Multimodal Transformers for biomedical text and Knowledge Graph data

SungBalance/tf-metal-experiments

TensorFlow Metal Backend on Apple Silicon Experiments (just for fun)

SungBalance/torch-test

SungBalance/vgpu_unlock

Unlock vGPU functionality for consumer grade GPUs.

SungBalance/vllm-fix

A high-throughput and memory-efficient inference and serving engine for LLMs