bit-50

Model overview

bit-50 is published by google as an image-classification model. The captured configuration identifies BitForImageClassification with model type bit. According to the model card, it implements Big Transfer pre-training of ResNet-like architectures for transfer across vision datasets.

Recorded capabilities

Use cases in the source record

• ImageNet-style image classification into 1,000 classes using the card's BitImageProcessor workflow.
• Transfer-learning experiments of the kind described in the BiT paper abstract across small and large vision datasets.

Limitations and unknowns

• No parameter count was extracted from this record.
• No context-window value applies to this image-classification record.
• Accuracy figures are quoted paper claims and were not independently verified.
• Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: google/bit-50

Captured: Unknown. Processed: 2026-09-07T19:34:45.713708+00:00.

Big Transfer (BiT) The BiT model was proposed in Big Transfer (BiT): General Visual Representation Learning by Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Joan Puigcerver, Jessica Yung, Sylvain Gelly, Neil Houlsby. BiT is a simple recipe for scaling up pre-training of ResNet -like architectures (specifically, ResNetv2). The method results in significant improvements for transfer learning. Disclaimer: The team releasing ResNet did not write a model card for this model so this model card has been written by the Hugging Face team. Model description The abstract from the paper is the following: Transfer of pre-trained representatio…