jonataslaw
VP of Engineering from Iris Finance. Developer and Lawyer. Passionate about dart and productivity hacks.
IrisDublin, Ireland
jonataslaw's Stars
Significant-Gravitas/Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
tauri-apps/tauri
Build smaller, faster, and more secure desktop applications with a web frontend.
CompVis/stable-diffusion
A latent text-to-image diffusion model
twitter/the-algorithm
Source code for Twitter's Recommendation Algorithm
ggerganov/llama.cpp
LLM inference in C/C++
preactjs/preact
⚛️ Fast 3kB React alternative with the same modern API. Components & Virtual DOM.
lerna/lerna
:dragon: Lerna is a fast, modern build system for managing and publishing multiple JavaScript/TypeScript packages from the same repository.
tloen/alpaca-lora
Instruct-tune LLaMA on consumer hardware
huggingface/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
nltk/nltk
NLTK Source
yoavbls/pretty-ts-errors
🔵 Make TypeScript errors prettier and human-readable in VSCode 🎀
BlinkDL/RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
artidoro/qlora
QLoRA: Efficient Finetuning of Quantized LLMs
manticoresoftware/manticoresearch
Easy to use open source fast database for search | Good alternative to Elasticsearch now | Drop-in replacement for E in the ELK soon
zilliztech/GPTCache
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
Instruction-Tuning-with-GPT-4/GPT-4-LLM
Instruction Tuning with GPT-4
isar/isar
Extremely fast, easy to use, and fully async NoSQL database for Flutter
facebookresearch/encodec
State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.
google-research/t5x
juncongmoo/chatllama
ChatLLaMA 📢 Open source implementation for LLaMA-based ChatGPT runnable in a single GPU. 15x faster training process than ChatGPT
nightmare-space/speed_share
Speed Share is a highly available file sharing terminal on LAN(local area network) like airdrop developed by flutter framework.
alexmercerind/flutter_acrylic
Flutter library for window acrylic, mica & transparency effects.
Shivanandroy/simpleT5
simpleT5 is built on top of PyTorch-lightning⚡️ and Transformers🤗 that lets you quickly train your T5 models.
akoksal/LongForm
Reverse Instructions to generate instruction tuning data with corpus examples
HuangLK/llama-deepspeed
train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism
ZrrSkywalker/LLaMA-Adapter
Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
Durham/RWKV-finetune-script
Script and instruction how to fine-tune large RWKV model on your data for Alpaca dataset
iantbutler01/rwkv-raven-qlora-4bit-instruct
A finetuning pipeline for instruct tuning Raven 14bn using QLORA 4bit and the Ditty finetuning library
RWKV/RWKV-cpp-node
Node.js implementation binding for the RWKV.cpp module
YOUSSSOF/Shoe-Commerce
modern e-commerce store built in flutter with help of GetX.