shirakiin commited on
Commit
e3ffd1a
·
verified ·
1 Parent(s): 945e427

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -18,6 +18,8 @@ This model card provides *FastVLM-0.5B converted for LiteRT* that are ready for
18
 
19
  FastVLM was introduced in [FastVLM: Efficient Vision Encoding for Vision Language Models](https://www.arxiv.org/abs/2412.13303). *(CVPR 2025)*, this model demonstrates improvement in time-to-first-token (TTFT) with performance and is suitable for edge device deployment.
20
 
 
 
21
  *Disclaimer*: This model converted for LiteRT is licensed under the [Apple Machine Learning Research Model License Agreement](https://huggingface.co/apple/deeplabv3-mobilevit-small/blob/main/LICENSE). The model is converted and quantized from PyTorch model weight into the LiteRT/Tensorflow-Lite format (no retraining or further customization).
22
 
23
  # How to Use
 
18
 
19
  FastVLM was introduced in [FastVLM: Efficient Vision Encoding for Vision Language Models](https://www.arxiv.org/abs/2412.13303). *(CVPR 2025)*, this model demonstrates improvement in time-to-first-token (TTFT) with performance and is suitable for edge device deployment.
20
 
21
+ The model is also converted for Qualcomm NPUs, see more details in this [blogpost](https://developers.googleblog.com/unlocking-peak-performance-on-qualcomm-npu-with-litert/).
22
+
23
  *Disclaimer*: This model converted for LiteRT is licensed under the [Apple Machine Learning Research Model License Agreement](https://huggingface.co/apple/deeplabv3-mobilevit-small/blob/main/LICENSE). The model is converted and quantized from PyTorch model weight into the LiteRT/Tensorflow-Lite format (no retraining or further customization).
24
 
25
  # How to Use