Alternatives and similar repositories for gpt-3

Users that are interested in gpt-3 are comparing it to the libraries listed below

• openai / gpt-2
  Code for the paper "Language Models are Unsupervised Multitask Learners"
  ☆23,680Updated 10 months ago
• openai / image-gpt
  ☆2,066Updated 3 years ago
• chenfei-wu / TaskMatrix
  ☆34,443Updated last year
• EleutherAI / gpt-neo
  An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
  ☆8,295Updated 3 years ago
• elyase / awesome-gpt3
  ☆4,568Updated last year
• deepspeedai / DeepSpeed
  DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
  ☆38,997Updated this week
• openai / tiktoken
  tiktoken is a fast BPE tokeniser for use with OpenAI's models.
  ☆14,829Updated 3 months ago
• facebookresearch / metaseq
  Repo for external large-scale work
  ☆6,530Updated last year
• karpathy / minGPT
  A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
  ☆22,108Updated 10 months ago
• kingoflolz / mesh-transformer-jax
  Model parallel transformers in JAX and Haiku
  ☆6,338Updated 2 years ago
• tatsu-lab / stanford_alpaca
  Code and documentation to train Stanford's Alpaca models, and generate the data.
  ☆30,040Updated 11 months ago
• EleutherAI / gpt-neox
  An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
  ☆7,228Updated last week
• google-research / google-research
  Google Research
  ☆35,790Updated this week
• FMInference / FlexLLMGen
  Running large language models on a single GPU for throughput-oriented scenarios.
  ☆9,338Updated 7 months ago
• meta-llama / llama
  Inference code for Llama models
  ☆58,399Updated 4 months ago
• facebookresearch / fairseq
  Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
  ☆31,543Updated last week
• triton-lang / triton
  Development repository for the Triton language and compiler
  ☆15,881Updated this week
• LAION-AI / Open-Assistant
  OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamical…
  ☆37,375Updated 10 months ago
• microsoft / JARVIS
  JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
  ☆24,182Updated 8 months ago
• google-research / bert
  TensorFlow code and pre-trained models for BERT
  ☆39,244Updated 10 months ago
• NVIDIA / Megatron-LM
  Ongoing research training transformer models at scale
  ☆12,600Updated this week
• microsoft / unilm
  Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
  ☆21,420Updated 2 weeks ago
• google / trax
  Trax — Deep Learning with Clear Code and Speed
  ☆8,223Updated 2 months ago
• lm-sys / FastChat
  An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
  ☆38,751Updated 2 weeks ago
• acheong08 / ChatGPT
  Reverse engineered ChatGPT API
  ☆28,039Updated last year
• facebookresearch / pytext
  A natural language modeling framework based on PyTorch
  ☆6,325Updated 2 years ago
• horovod / horovod
  Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
  ☆14,512Updated last month
• allenai / allennlp
  An open-source NLP research library, built on PyTorch.
  ☆11,851Updated 2 years ago
• tloen / alpaca-lora
  Instruct-tune LLaMA on consumer hardware
  ☆18,917Updated 10 months ago
• zihangdai / xlnet
  XLNet: Generalized Autoregressive Pretraining for Language Understanding
  ☆6,183Updated 2 years ago