---
license: apache-2.0
tags:
- mirror
- xai
- image-classification
- vit
- vision-transformer
- imagenet
---

# ViT-B/16 ImageNet (Google) — xaitalk mirror

This is a **bit-identical mirror** of the canonical artifact from Google Research.

The mirror exists only as a resilience fallback for the
[xaitalk](https://github.com/xaitalk/xaitalk) library — the upstream remains
authoritative. All credit and licensing for the model belong to the original
authors.

## Attribution

| Field | Value |
|---|---|
| **Original authors** | Google Research |
| **Upstream (authoritative)** | https://huggingface.co/google/vit-base-patch16-224 |
| **Source repo** | https://github.com/google-research/vision_transformer |
| **Paper** | https://arxiv.org/abs/2010.11929 (Dosovitskiy et al. 2020) |
| **License** | `apache-2.0` (inherited from upstream — please respect upstream's terms) |
| **Mirror file** | `pytorch_model.bin` |
| **SHA-256** | `5f17067668129d23b52524f90a805e7d9914c276d90a59a13ebe81a09e40ceca` |
| **Size** | 346,351,599 bytes (330.3 MB) |

## How xaitalk loads this file

```python
from xaitalk.hub import ensure_model
weights_path = ensure_model("vit-base-patch16-224")
# Tries the canonical upstream first; falls back to this xaitalk mirror
# automatically if upstream is unreachable.
```

## Why mirror?

xaitalk's research-grade reproducibility claim relies on every weight file
being recoverable years from now. We mirror artifacts ≤ 2.5 GB under
`xaitalk/*-mirror` so the pipeline survives upstream URL changes, repo
renames, or deletions. Bit-level parity with the canonical is asserted in
CI via `python -m xaitalk.hub verify-mirrors`.

## Citation

If you use this model, **please cite the original paper** (not the mirror):

```
https://arxiv.org/abs/2010.11929 (Dosovitskiy et al. 2020)
```