YeonwooSung

followers

following

stars

Seoul

Yeonwoo Sung's starred repositories

whisper.cpp

Port of OpenAI's Whisper model in C/C++

Language:C++MIT33279 306 1236

llama3

The official Meta Llama 3 GitHub site

Language:PythonNOASSERTION23451 193 197

mdBook

Create book from markdown files. Like Gitbook but implemented in Rust

Language:RustMPL-2.017315 123 1264

vector

A high-performance observability data pipeline.

Language:RustMPL-2.017075 151 7464

valkey

A flexible distributed key-value datastore that supports both caching and beyond caching workloads.

Language:CNOASSERTION14834 97 245

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Language:PythonApache-2.012456 78 785

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.

Language:PythonMIT12080 90 335

cvat

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

Language:TypeScriptMIT11903 183 4000

garnet

Garnet is a remote cache-store from Microsoft Research that offers strong performance (throughput and latency), scalability, storage, recovery, cluster sharding, key migration, and replication features. Garnet can work with existing Redis clients.

Language:C#MIT9819 68 142

mistral-src

Reference implementation of Mistral AI 7B v0.1 model.

Language:Jupyter NotebookApache-2.08772 116 115

text-generation-inference

Large Language Model Text Generation Inference

Language:PythonApache-2.08433 99 1217

corenet

CoreNet: A library for training deep neural networks

Language:PythonNOASSERTION6800 63 19

StackExchange.Redis

General purpose redis client

Language:C#NOASSERTION5850 316 1972

readyset

Readyset is a MySQL and Postgres wire-compatible caching layer that sits in front of existing databases to speed up queries and horizontally scale read throughput. Under the hood, ReadySet caches the results of cached select statements and incrementally updates these results over time as the underlying data changes.

Language:RustNOASSERTION4068 23 520

torchtune

A Native-PyTorch Library for LLM Fine-tuning

Language:PythonBSD-3-Clause3640 43 374

redka

Redis re-implemented with SQLite

Language:GoBSD-3-Clause3276 28 19

mistral.rs

Blazingly fast LLM inference.

Language:RustMIT3027 31 161

cohere-toolkit

Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

Language:TypeScriptMIT2569 35 33

dbrx

Code examples and resources for DBRX, a large language model developed by Databricks

Language:PythonNOASSERTION2484 40 22

PurpleLlama

Set of tools to assess and improve LLM security.

Language:PythonNOASSERTION2178 34 25

index_advisor

PostgreSQL Index Advisor

Language:PLpgSQLPostgreSQL1583 6 5

lingua-go

The most accurate natural language detection library for Go, suitable for short text and mixed-language text

Language:GoApache-2.01129 11 35

llm2vec

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

Language:PythonMIT847 18 103

lemmatization-lists

Machine-readable lists of lemma-token pairs in 23 languages.

ODbL-1.0316 18 9

candle-vllm

Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.

Language:RustMIT177 7 33

llama-inference

experiments with inference on llama

Language:Python103 3 3

generative-bi-using-rag

A solution guidance for Generative BI using Amazon Bedrock, Amazon OpenSearch with RAG

Language:PythonMIT-071 6 6

postgresql_cluster

PostgreSQL High-Availability Cluster (based on "Patroni" and DCS "etcd" or "consul"). Automating with Ansible.

Language:JinjaMIT200

vision-search

Image search engine

Language:PythonGPL-3.02 30

SWE-agent

SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models

Language:PythonMIT100