From Wikipedia, the free encyclopedia
Initial releaseJune 9, 2021; 2 years ago (2021-06-09)
LicenseOpen-source Edit this on Wikidata

GPT-J or GPT-J-6B is an open-source large language model (LLM) developed by EleutherAI in 2021.[1] As the name suggests, it is a generative pre-trained transformer model designed to produce human-like text that continues from a prompt. The optional "6B" in the name refers to the fact that it has 6 billion parameters.[2]


GPT-J is a GPT-3-like model with 6 billion parameters.[3] Like GPT-3, it is an autoregressive, decoder-only transformer model designed to solve natural language processing (NLP) tasks by predicting how a piece of text will continue.[1]

Its architecture differs from GPT-3 in three main ways.[1]

  • The attention and feedforward neural network were computed in parallel during training, allowing for greater efficiency.
  • The GPT-J model uses Rotary Position Embeddings, which has been found to be a superior method of injecting positional information into transformers.[4][5]
  • GPT-J uses dense attention instead of efficient sparse attention, as used in GPT-3.

Beyond that, the model has 28 transformer layers and 16 attention heads. Its vocabulary size is 50257 tokens, the same size as GPT-2's.[2] It has a context window size of 2048 tokens.[6]

It was trained on the Pile dataset,[2][3] using the Mesh Transformer JAX library in JAX to handle the parallelization scheme.[2][7]


GPT-J was designed to generate English text from a prompt. It was not designed for translating or generating text in other languages or for performance without first fine-tuning the model for a specific task.[2] Nonetheless, GPT-J performs reasonably well even without fine-tuning, even in translation (at least from English to French).[8]

When neither is fine-tuned, GPT-J-6B performs almost as well as the 6.7 billion parameter GPT-3 (Curie) on a variety of tasks.[3] It even outperforms the 175 billion parameter GPT-3 (Davinci) on code generation tasks.[9][10] With fine-tuning, it outperforms an untuned GPT-3 (Davinci) on a number of tasks.[1]

Like all LLMs, it is not programmed to give factually accurate information, only to generate text based on probability.[2]


The untuned GPT-J is available on EleutherAI's website,[11] NVIDIA's Triton Inference Server,[12] and NLP Cloud's website.[13] Cerebras[1] and Amazon Web Services[14][15] offer services to fine-tune the GPT-J model for company-specific tasks. Graphcore offers both fine-tuning and hosting services for the untuned GPT-J, as well as offering to host the fine-tuned models after they are produced.[16] CoreWeave offers hosting services for both the untuned GPT-J and fine-tuned variants.[17][18]

In March 2023, Databricks released Dolly, an Apache-licensed, instruction-following model created by fine-tuning GPT-J on the Stanford Alpaca dataset.[19] NovelAI's Sigurd[20] and Genji-JP 6B[21] models are both fine-tuned versions of GPT-J. They also offer further fine-tuning services to produce and host custom models.[22]

EleutherAI has received praise from Cerebras,[1] GPT-3 Demo,[3] NLP Cloud,[13] and Databricks[19] for making the model open-source, and its open-source status is often cited as a major advantage when choosing which model to use.[10][16][23]


  1. ^ a b c d e f Vassilieva, Natalia (22 June 2022). "Cerebras Makes It Easy to Harness the Predictive Power of GPT-J". Cerebras. Retrieved 14 June 2023.
  2. ^ a b c d e f "GPT-J 6B". Hugging Face. Retrieved 13 June 2023.
  3. ^ a b c d "GPT-J". GPT-3 Demo. Retrieved 13 June 2023.
  4. ^ Biderman, Stella; Black, Sid; Foster, Charles; Gao, Leo; Hallahan, Eric; He, Horace; Wang, Ben; Wang, Phil (20 April 2021). "Rotary Embeddings: A Relative Revolution". EleutherAI. Retrieved 14 June 2023. In general we have found that across a large suite of setups including regular, linear, and local self-attention, it either matches or surpasses all other methods currently available for injecting positional information into transformers.
  5. ^ Su, Jianlin; Lu, Yu; Pan, Shengfeng; Murtadha, Ahmed; Wen, Bo; Liu, Yunfeng (9 August 2022). "RoFormer: Enhanced Transformer with Rotary Position Embedding". arXiv:2104.09864 [cs.CL].
  6. ^ "GPT-J". GitHub. Hugging Face. Retrieved 23 June 2023.
  7. ^ Wang, Ben; Komatsuzaki, Aran (May 2021). "Mesh Transformer JAX". GitHub. Retrieved 13 June 2023.
  8. ^ Forefront (14 October 2021). "GPT-J-6B: An Introduction to the Largest Open Source GPT Model | Forefront". Medium. Forefront. Retrieved 13 June 2023.
  9. ^ Mueller, Vincent (26 August 2021). "How you can use GPT-J". Medium. Retrieved 23 June 2023.
  10. ^ a b "GPT-J Reviews". Slashdot. Retrieved 23 June 2023.
  11. ^ "Test the EAI models". EleutherAI. 2021. Retrieved 30 June 2023.
  12. ^ Timonin, Denis; Hsueh, Bo Yang; Singal, Dhruv; Nguyen, Vinh (3 August 2022). "Deploying GPT-J and T5 with NVIDIA Triton Inference Server". NVIDIA. Retrieved 30 June 2023.
  13. ^ a b Vettier, Pauline (16 September 2021). "NLP Cloud now supports GPT-J, the open-source GPT-3 alternative" (Press release). Grenoble, France: NLP Cloud. Retrieved 30 June 2023.
  14. ^ Awrahman, Zmnako; Tsitiridou, Anastasia Pachni; Patel, Dhawalkumar; Huilgol, Rahul; Bains, Roop; Stobieniecka, Wioletta (12 June 2023). "Fine-tune GPT-J using an Amazon SageMaker Hugging Face estimator and the model parallel library". Amazon Web Services. Retrieved 30 June 2023.
  15. ^ Schmid, Philipp (11 January 2022). "Deploy GPT-J 6B for inference using Hugging Face Transformers and Amazon SageMaker". Hugging Face. Retrieved 30 June 2023.
  16. ^ a b Liguori, Sofia (9 June 2023). "Fine-Tune GPT-J: A Cost-Effective GPT-4 Alternative for Many NLP Tasks". Graphcore. Retrieved 23 June 2023.
  17. ^ "GPT-J-6B". CoreWeave. 23 June 2023. Retrieved 30 June 2023.
  18. ^ Hjelm, Max. "CoreWeave Powers a World of Possibility with GPT-J". CoreWeave. Retrieved 30 June 2023.
  19. ^ a b Conover, Mike; Hayes, Matt; Mathur, Ankit; Meng, Xiangrui; Xie, Jianwei; Wan, Jun; Ghodsi, Ali; Wendell, Patrick; Zaharia, Matei (24 March 2023). "Hello Dolly: Democratizing the magic of ChatGPT with open models". Databricks. Retrieved 18 June 2023.
  20. ^ NovelAI (9 May 2022). "The faces of NovelAI's AI Models: Part 1". Medium. Retrieved 1 July 2023.
  21. ^ NovelAI (3 November 2021). "Data Efficient Language Transfer with GPT-J". Medium. Retrieved 1 July 2023.
  22. ^ NovelAI (29 July 2021). "Introducing Custom AI Modules". Medium. Retrieved 1 July 2023.
  23. ^ Shiraly, Karthik (26 February 2023). "See GPT-J vs. GPT-3 Go Head-to-Head on Popular Language Tasks". Retrieved 23 June 2023.