xiangjjj

ccsum

trlx

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

full

Evaluation of open-domain dialog using Follow-Ups Log-Likelihood (FULL) https://aclanthology.org/2022.coling-1.40/

trl

Train transformer language models with reinforcement learning.

llm-foundry

LLM training code for Databricks foundation models

DL-Hard

Deep Learning Hard (DL-HARD) is a new annotated dataset extending TREC Deep Learning benchmark.

alpaca-lora

Instruct-tune LLaMA on consumer hardware

RL4LMs

A modular RL library to fine-tune language models to human preferences

alexa-teacher-models

dolly

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

DialoGPT

Large-scale pretraining for dialogue

Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

llama

Inference code for Llama models

dialog-inpainting

FlexGen

Running large language models on a single GPU for throughput-oriented scenarios.

deep-learning-containers

AWS Deep Learning Containers (DLCs) are a set of Docker images for training and serving models in TensorFlow, TensorFlow 2, PyTorch, and MXNet.

ColossalAI

Making large AI models cheaper, faster and more accessible

cdx_toolkit

A toolkit for CDX indices such as Common Crawl and the Internet Archive's Wayback Machine

huggingface_hub

The official Python client for the Huggingface Hub.

hh-rlhf

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

Megatron-LM

Ongoing research training transformer models at scale

ReFinED

ReFinED is an efficient and accurate entity linking (EL) system.

the-pile

LaMDA-rlhf-pytorch

Open-source pre-training implementation of Google's LaMDA in PyTorch. Adding RLHF similar to ChatGPT.

cc-crawl-statistics

Statistics of Common Crawl monthly archives mined from URL index files

examples

📝 Examples of how to use Neptune for different use cases and with various MLOps tools

news-please

news-please - an integrated web crawler and information extractor for news that just works

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.