liuyhwangyh

gpt4all

GPT4All: Chat with Local LLMs on Any Device

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

requests

A simple, yet elegant, HTTP library.

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

llama_index

LlamaIndex is a data framework for your LLM applications

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

duckdb

DuckDB is an analytical in-process SQL database management system

guidance

A guidance language for controlling large language models.

arrow

Apache Arrow is a multi-language toolbox for accelerated data interchange and in-memory processing

sympy

A computer algebra system written in pure Python

MOSS

An open-source tool-augmented conversational language model from Fudan University

node_exporter

Exporter for machine metrics

Awesome-Diffusion-Models

A collection of resources and papers on Diffusion Models

OpenLLM

Run any open-source LLMs, such as Llama 2, Mistral, as OpenAI compatible API endpoint in the cloud.

magika

Detect file content types with deep learning

jsonschema2pojo

Generate Java types from JSON or JSON Schema and annotate those types for data-binding with Jackson, Gson, etc

FasterTransformer

Transformer related optimization, including BERT, GPT

OLMo

Modeling, training, eval, and inference code for OLMo

oboe

Oboe is a C++ library that makes it easy to build high-performance audio apps on Android.

python

Docker Official Image packaging for Python

uvadlc_notebooks

Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023

Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

awesome-chatgpt-dataset

Unlock the Power of LLM: Explore These Datasets to Train Your Own ChatGPT!

H2O

[NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.

xFasterTransformer

mayhem

The Python asyncio tutorial I wish existed earlier

GEOparse

Python library to access Gene Expression Omnibus Database (GEO)

sseclient

geofetch

Builds a PEP from SRA or GEO accessions

modelscope-studio