← Back to Explorer
Pending

GPT-J-6B (2021)

GPT-J-6B is a large language model released by EleutherAI, released under the Apache-2.0 license, with a claimed knowledge cutoff of 2021-06-04. Its weights, configuration, and tokenizer files have been cryptographically hashed and are queued for on-chain attestation by Weight Registry.

Description

EleutherAI's open reproduction of GPT-3-class autoregressive transformers, released while GPT-3 itself remained closed/API-only.

Metadata

Type
LLM
Issuer
EleutherAI
License
Apache-2.0
Size
22.55 GB
Knowledge cutoff
2021-06-04
Source
https://huggingface.co/EleutherAI/gpt-j-6b
Revision
47e169305d2e8376be1d31e765533382721b2cc1

Hugging Face stats

352,598 downloads on Hugging Face · 1,525 likes · pipeline: text-generation · library: transformers

transformerspytorchtfjaxgptjtext-generationcausal-lmenendpoints_compatible

Weight Hashes

Weights file
pytorch_model.bin · 22.55 GB
SHA-2560e183edc2025ecfdba4429ba43c960224103b3c3dc26616503cdc2158a3d6c93
SHA3-256b60ad49e8392c100b1ea260f16e2309e4936235939090f9aa3abe8e8aa1bd90d
BLAKE3630bbe24d5eea11f29d656352a09ede70c795394050dedf8b788ed89e67b379f
Config file
config.json · 930 B
SHA-2569328fc6e157f344fbbcd8c605a876c1fe2f7441a40a00c3046f4e8f99ab619e6
SHA3-256b7197c978ba8aa63fffb8838563784c99896dcc3050bea5dd0c96336cefd8096
BLAKE37abce05ed9c86c975b6e34901fc6e5ca1e596759f75ae3ae61c17be64f8fb727
Tokenizer file
tokenizer.json · 1.31 MB
SHA-256f758fc1ee05a0775387ad8fa3983fab0c40e4a05cf6b7aea00a29e696cd6205c
SHA3-25645849b79449b24c1dba401e418edb665e5a32fa0fcd5d2f1e5f37e194ba76615
BLAKE3b1a41f564a031171a07694d9eaba89d4422495fbbe99a50484dc69c54c08df37

Verify it yourself

curl -L -o "pytorch_model.bin" "https://huggingface.co/EleutherAI/gpt-j-6b/resolve/47e169305d2e8376be1d31e765533382721b2cc1/pytorch_model.bin"
sha256sum "pytorch_model.bin"

Expected SHA-256: 0e183edc2025ecfdba4429ba43c960224103b3c3dc26616503cdc2158a3d6c93