README.md

---
license: other
license_name: apple
license_link: https://github.com/apple/ml-fastvlm/blob/main/LICENSE
language:
- en
pipeline_tag: image-text-to-text
tags:
- multimodal
library_name: transformers
---

# FastVLM-0.5B-Stage2

## Introduction

This is FastVLM-0.5B-Stage2, a multimodal language model that can understand things visually, being agentic, understand long videos and capture events, and generate structured outputs.

This model is exported from Github [apple/ml-fastvlm](https://github.com/apple/ml-fastvlm).

Model's weight: [llava-fastvithd_0.5b_stage2.zip](https://ml-site.cdn-apple.com/datasets/fastvlm/llava-fastvithd_0.5b_stage2.zip).


### Usage
```python
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = 'FastVLM-0.5B-Stage2'
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype='auto', trust_remote_code=True)
```

### Export to MNN
```python
git clone https://github.com/alibaba/MNN
cd MNN/transformers/llm/export
python llmexport.py --path /path/to/FastVLM-0.5B-Stage2 --export mnn
```


## Citation

If you find our work helpful, feel free to give us a cite.

```
@InProceedings{fastvlm2025,
  author = {Pavan Kumar Anasosalu Vasu, Fartash Faghri, Chun-Liang Li, Cem Koc, Nate True, Albert Antony, Gokul Santhanam, James Gabriel, Peter Grasch, Oncel Tuzel, Hadi Pouransari},
  title = {FastVLM: Efficient Vision Encoding for Vision Language Models},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month = {June},
  year = {2025},
}{2023}
```