EasyDeL is an OpenSource Library to make your training faster and more Optimized With cool Options for training and serving Both in Python And Mojo🔥

⚗️ distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency.

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Forked repo from https://github.com/EleutherAI/lm-evaluation-harness/commit/1f66adc

S2APLER: S2 Agglomeration of Papers with Low Error Rate (it's for academic paper clustering)

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

LLM simple serving (tensor model parallel, pubsub, grpc)

Huggingface compatible implementation of RetNet (Retentive Networks, https://arxiv.org/pdf/2307.08621.pdf) including parallel, recurrent, and chunkwise forward.

The official GitHub page for the survey paper "A Survey of Large Language Models".

A framework for few-shot evaluation of autoregressive language models.

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

Official style files for papers submitted to venues of the Association for Computational Linguistics

This tool helps automatic generation of grammatically valid synthetic Code-mixed data by utilizing linguistic theories such as Equivalence Constant Theory and Matrix Language Theory.

KoAlpaca: Korean Alpaca Model based on Stanford Alpaca (feat. LLAMA and Polyglot-ko)

A unified, comprehensive and efficient recommendation library

Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways

The Hugging Face course

internal-only

Korean LegalQA using SentenceKoBART

KakaoBrain KoGPT (Korean Generative Pre-trained Transformer)

A set of available examples in recommender system.

A collection of notebooks for Natural Language Processing from NLP Town