xiangjjj

xiangjjj's Stars

• Significant-Gravitas/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.

  Language:Python169k1.5k3k44.6k

• meta-llama/llama

  Inference code for Llama models

  Language:Python56.9k5261k9.6k

• hpcaitech/ColossalAI

  Making large AI models cheaper, faster and more accessible

  Language:Python38.9k3851.7k4.3k

• LAION-AI/Open-Assistant

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

  Language:Python37.1k4331.6k3.2k

• facebookresearch/fairseq

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

  Language:Python30.7k4264.2k6.4k

• tloen/alpaca-lora

  Instruct-tune LLaMA on consumer hardware

  Language:Jupyter Notebook18.7k1544692.2k

• NVIDIA/Megatron-LM

  Ongoing research training transformer models at scale

  Language:Python10.9k1668012.4k

• databrickslabs/dolly

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

  Language:Python10.8k1391621.2k

• huggingface/trl

  Train transformer language models with reinforcement learning.

  Language:Python10.4k771.3k1.3k

• FMInference/FlexGen

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

  Language:Python9.1k11181540

• CarperAI/trlx

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

  Language:Python4.5k51291473

• mosaicml/llm-foundry

  LLM training code for Databricks foundation models

  Language:Python4.1k48385532

• microsoft/DialoGPT

  Large-scale pretraining for dialogue

  Language:Python2.4k5584341

• allenai/RL4LMs

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

  Language:Python2.2k2459192

• huggingface/huggingface_hub

  The official Python client for the Huggingface Hub.

  Language:Python2.2k581k567

• fhamborg/news-please

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

  Language:Python2.1k54180431

• microsoft/Megatron-DeepSpeed

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

  Language:Python1.9k24183343

• anthropics/hh-rlhf

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

  1.6k200129

• EleutherAI/the-pile

  Language:Python1.5k30100131

• aws/deep-learning-containers

  AWS Deep Learning Containers are pre-built Docker images that make it easier to run popular deep learning frameworks and tools on AWS.

  Language:Python1k57244467

• conceptofmind/LaMDA-rlhf-pytorch

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

  Language:Python46723776

• amazon-science/alexa-teacher-models

  Language:Python36336727

• amazon-science/ReFinED

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

  Language:Python197182642

• commoncrawl/cc-crawl-statistics

  Statistics of Common Crawl monthly archives mined from URL index files

  Language:Python16318811

• cocrawler/cdx_toolkit

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

  Language:Python160112031

• google-research/dialog-inpainting

  97736

• neptune-ai/examples

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

  Language:Jupyter Notebook7911732

• grill-lab/DL-Hard

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

  36534

• maximedb/full

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

  Language:Python8111

• amazon-science/ccsum

  Language:Python4521