---
library_name: transformers
tags:
- testing
- image-text-to-text
---
# Tiny Xiaomi-Lens-0 processor

Processor-only test fixture using the tiny BPE tokenizer from
[hf-internal-testing/tiny-processor-qwen3_vl](https://huggingface.co/hf-internal-testing/tiny-processor-qwen3_vl/tree/8629850bf551ef61426c577885421520a1eacee7)
and the processor configuration, tokenizer settings, and chat template from
[guarin/Xiaomi-Lens-0](https://huggingface.co/guarin/Xiaomi-Lens-0/tree/1fe02dea90bfaaaf1d1311dc187a4466fdb9a1b8).

Xiaomi control tokens are added to the tiny vocabulary. Token IDs are local to this
fixture and are not compatible with the full model weights. Image and video size limits (784–3136 pixels) and patch size (4) use the tiny Qwen fixture settings for fast unit tests. The image min_pixels/max_pixels aliases match those limits. Other processor settings, the chat template, and tokenizer settings come from Xiaomi-Lens-0. No model weights are included.
Requires a Transformers version supporting XiaomiLens0Processor.

```python
from transformers import AutoProcessor
processor = AutoProcessor.from_pretrained("hf-internal-testing/tiny-processor-xiaomi_lens0")
```