xu-song

bert-as-language-model

BERT as language model, fork from https://github.com/google-research/bert

hexo-auto-category

Generate categories automatically for each post in Hexo

k-plug

K-PLUG: Knowledge-injected Pre-trained Language Model for Natural Language Understanding and Generation in E-Commerce (Findings of EMNLP 2021)

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

chat.petals.ml

Chatbot web app + HTTP and Websocket endpoints for BLOOM-176B inference with the Petals client

CrossWOZ

A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset

hexo

A fast, simple & powerful blog framework, powered by Node.js.

hred-tf

Hierarchical Recurrent Encoder-Decoder in TensorFlow

machine-learning

petals

🌸 Run 100B+ language models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

tokenizer-arena

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

xu-song

cc_net

Tools to download and cleanup Common Crawl data

cpython

The Python programming language

DeepSpeed

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

DeepSpeedExamples

Example models using DeepSpeed

FasterTransformer

Transformer related optimization, including BERT, GPT

gradio

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

icetk

A unified tokenization tool for Images, Chinese and English.

LLaMA-Factory

Unify Efficient Fine-Tuning of 100+ LLMs

Megatron-LM

Ongoing research training transformer models at scale

MOSS

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

openai-python

The OpenAI Python library provides convenient access to the OpenAI API from applications written in the Python language.

opencompass

OpenCompass is an LLM evaluation platform, supporting a wide range of models (InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

self-instruct

Aligning pretrained language models with instruction data generated by themselves.

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

tqdm

:zap: A Fast, Extensible Progress Bar for Python and CLI