Efficient Triton Kernels for LLM Training

You like pytorch? You like micrograd? You love tinygrad! ❤️

Calculate perplexity on a text with pre-trained language models. Support MLM (eg. DeBERTa), recurrent LM (eg. GPT3), and encoder-decoder LM (eg. Flan-T5).

The fastest way to create an HTML app

Waydroid uses a container-based approach to boot a full Android system on a regular GNU/Linux system like Ubuntu.

Developing chatbot using laoNLP case study: Department of Computer Science

🪿 Han (ห่าน) is a project under PyThaiNLP project that want to create the experiment for Thai language.

Fast lexical search library implementing BM25 in Python using Numpy and Scipy

Porting AsteroidOS to the Google Pixel Watch (version 2)

An Extensible Deep Learning Library

Issues and discussions around RISC-V support in AOSP.

A nanoGPT pipeline packed in a spreadsheet

An open source implementation of CLIP.

Cramming the training of a (BERT-type) language model into limited compute.

Fish-like autosuggestions for zsh

BERT score for text generation

High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.

Thai Universal Dependency Treebank

A Jax-based library for designing and training transformer models from scratch.

ShanNLP experimental project inspired by PythaiNLP

Open compressed files in Python

Chat Templates for 🤗 HuggingFace Large Language Models

Simply shuffle a big file that does not fit in memory

Kolmogorov Arnold Networks

High-performance retrieval engine for unstructured data

Create Magic Story!

Thai NLP Task Powered by Prompt

Evaluating LLMs with fewer examples

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

WangchanX Fine-tuning Pipeline