LAION

weights

open(56 ungated laion/CLIP-* checkpoints on the Hub - 50 MIT, 4 Apache-2.0 and 2 declaring none)

data

open(the DataComp-1B corpus behind the DataComp.XL checkpoints is published ungated under CC-BY-4.0

code

open(open_clip ships the full contrastive pretraining pipeline - data loading, training loop, distributed launch scripts and ImageNet zero-shot evaluation)

license

MIT(OSI)

OpenCLIP publishes the training corpus, the pipeline that consumed it and an OSI license over the weights, which is the fullest release case in this category. The original LAION-2B corpus these checkpoints were trained on no longer resolves under its own name; it now points to the re-filtered ReLAION release behind a click-through gate, which counts as released rather than merely documented.

• https://huggingface.co/api/datasets/laion/relaion2B-en-research-safe recorded 2026-09-11

  `id: laion/relaion2B-en-research-safe`, `gated: auto`, `private: false`, `disabled: false` - and the request for laion/laion2B-en redirects here.

• https://huggingface.co/api/datasets/mlfoundations/datacomp_1b recorded 2026-09-11

  gated: false; license cc-by-4.0 - DataComp-1B, the corpus behind the DataComp.XL checkpoints, is published and ungated. This is the firmer footing for data:open than the LAION-2B path, whose original name now redirects to a re-filtered successor behind a gate.

• https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K/raw/main/README.md recorded 2026-09-11

  `license: mit`; 'A CLIP ViT-H/14 model trained with the LAION-2B English subset of LAION-5B ... using OpenCLIP'; a Training Data section naming the 2-billion-sample English subset.

• https://raw.githubusercontent.com/mlfoundations/open_clip/main/LICENSE recorded 2026-09-11

  the MIT permission grant verbatim - 'to deal in the Software without restriction' - over a 2012-2021 copyright by the open_clip authors.

• https://raw.githubusercontent.com/mlfoundations/open_clip/main/README.md recorded 2026-09-11

  'This repository is focused on training CLIP models'; documents `python -m open_clip_train.main` with train-data, epochs and imagenet-val arguments, plus single-node and SLURM multi-node launch recipes.

Adoption is measured as Hugging Face downloads summed across the OpenCLIP checkpoints LAION publishes, declared as a family: every laion/CLIP-* checkpoint across the LAION-2B, LAION-5B multilingual, DataComp and CommonPool lines, and the CoCa checkpoints open_clip ships beside them. Copies re-hosted on other accounts, such as timm's, are excluded as mirrors, so the figure is a floor on the library's use.

• https://huggingface.co/api/models?author=laion&search=CLIP&limit=100&sort=downloads&direction=-1 recorded 2026-10-17

  56 laion repos matching CLIP with `downloads` (trailing 30 days) summing to 9,556,334; the 50 declared CLIP-* checkpoints account for 9,555,823, led by CLIP-ViT-B-32-laion2B-s34B-b79K at 3,836,233. The other six are LLM runs named for gradient clipping and an OpenVINO int8 copy of OpenAI's CLIP.

• https://huggingface.co/api/models?author=laion&search=CoCa&limit=100&sort=downloads&direction=-1 recorded 2026-10-17

  4 laion CoCa checkpoints, all `library_name: open_clip`, with `downloads` summing to 16,298.

OpenCLIP posts real, published zero-shot ImageNet numbers and beats the original CLIP it reproduced, but the LAION-2B checkpoints are from an earlier generation, and SigLIP 2 leads them by five points on the same benchmark.

• https://raw.githubusercontent.com/mlfoundations/open_clip/main/README.md recorded 2026-09-11

  model table, ImageNet zero-shot acc.: ViT-H-14 LAION-2B 32B samples 78.0%; ViT-bigG-14 LAION-2B 34B samples 80.1%; ViT-L-14-quickgelu (Original CLIP) WIT 13B 75.5%.