Cao Ky Hieu (caokyhieu)

caokyhieu

Geek Repo

Company:Trinity College Dublin

Location:Dublin

Github PK Tool:Github PK Tool

Cao Ky Hieu's starred repositories

voice-engine

building blocks to create voice interface applications

Language:PythonLicense:GPL-3.0Stargazers:183Issues:0Issues:0

optimistix

Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/

Language:PythonLicense:Apache-2.0Stargazers:273Issues:0Issues:0

optax

Optax is a gradient processing and optimization library for JAX.

Language:PythonLicense:Apache-2.0Stargazers:1586Issues:0Issues:0

levanter

Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax

Language:PythonLicense:Apache-2.0Stargazers:476Issues:0Issues:0

diffrax

Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/

Language:PythonLicense:Apache-2.0Stargazers:1337Issues:0Issues:0

equinox

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

Language:PythonLicense:Apache-2.0Stargazers:1941Issues:0Issues:0

blackjax

BlackJAX is a Bayesian Inference library designed for ease of use, speed and modularity.

Language:PythonLicense:Apache-2.0Stargazers:769Issues:0Issues:0

lineax

Linear solvers in JAX and Equinox. https://docs.kidger.site/lineax

Language:PythonLicense:Apache-2.0Stargazers:329Issues:0Issues:0

WeightWatcher

The WeightWatcher tool for predicting the accuracy of Deep Neural Networks

Language:PythonLicense:Apache-2.0Stargazers:1420Issues:0Issues:0

chroma

the AI-native open-source embedding database

Language:RustLicense:Apache-2.0Stargazers:13880Issues:0Issues:0

M.I.L.E.S

M.I.L.E.S, a GPT-4-Turbo voice assistant, self-adapts its prompts and AI model, can play any Spotify song, adjusts system and Spotify volume, performs calculations, browses the web and internet, searches global weather, delivers date and time, autonomously chooses and retains long-term memories. Available for macOS and Windows.

Language:PythonLicense:MITStargazers:128Issues:0Issues:0

llama_index

LlamaIndex is a data framework for your LLM applications

Language:PythonLicense:MITStargazers:34109Issues:0Issues:0

rag-demystified

An LLM-powered advanced RAG pipeline built from scratch

Language:PythonLicense:Apache-2.0Stargazers:770Issues:0Issues:0

vllm

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

Language:PythonLicense:Apache-2.0Stargazers:24027Issues:0Issues:0

TradeMaster

TradeMaster is an open-source platform for quantitative trading empowered by reinforcement learning :fire: :zap: :rainbow:

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:1266Issues:0Issues:0

flash-attention

Fast and memory-efficient exact attention

Language:PythonLicense:BSD-3-ClauseStargazers:12698Issues:0Issues:0

awesome-large-audio-models

Collection of resources on the applications of Large Language Models (LLMs) in Audio AI.

Stargazers:478Issues:0Issues:0

SpeechGPT

SpeechGPT Series: Speech Large Language Models

Language:PythonLicense:Apache-2.0Stargazers:1125Issues:0Issues:0

LLMDataHub

A quick guide (especially) for trending instruction finetuning datasets

License:MITStargazers:2301Issues:0Issues:0

LLMLingua

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

Language:PythonLicense:MITStargazers:4287Issues:0Issues:0

mamba

Mamba SSM architecture

Language:PythonLicense:Apache-2.0Stargazers:11995Issues:0Issues:0

PowerfulPromptFT

[NeurIPS 2023 Main Track] This is the repository for the paper titled "Don’t Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner"

Language:PythonLicense:MITStargazers:71Issues:0Issues:0

streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

Language:PythonLicense:MITStargazers:6399Issues:0Issues:0

websockets

Library for building WebSocket servers and clients in Python

Language:PythonLicense:BSD-3-ClauseStargazers:5091Issues:0Issues:0

LLMAgentPapers

Must-read Papers on LLM Agents.

Stargazers:1522Issues:0Issues:0

text-generation-inference

Large Language Model Text Generation Inference

Language:PythonLicense:Apache-2.0Stargazers:8504Issues:0Issues:0

DeepSpeed

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

Language:PythonLicense:Apache-2.0Stargazers:34094Issues:0Issues:0

simulatrex-engine

Enable decision-making based on simulations

Language:PythonLicense:Apache-2.0Stargazers:217Issues:0Issues:0

ollama

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

Language:GoLicense:MITStargazers:82843Issues:0Issues:0

Vietnamese_LLMs

Dự án bao gồm: 1. Xây dựng bộ dữ Instructions Vietnamese (chất lượng, nhiều, và đa dạng). 2.LLM Training, Finetuning, Evaluating & Testing trên Open-source mô hình ngôn ngữ: Bloomz,T5, UL2, LLaMA (1&2), OpenLLaMA, GPT-J pythia etc. 3. Ứng dụng và Giao diện Người dùng (UI)

Language:PythonLicense:Apache-2.0Stargazers:196Issues:0Issues:0