Image-Text-to-Text
Transformers.js
ONNX
English
llava
text-generation
multimodal
qwen
conversational
Instructions to use onnx-community/nanoLLaVA-1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use onnx-community/nanoLLaVA-1.5 with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('image-text-to-text', 'onnx-community/nanoLLaVA-1.5');
Download onnx/vision_encoder_quantized.onnx from onnx-community/nanoLLaVA-1.5: direct link, hf CLI and curl.
- Browser
- Download file 405 MB
-
https://huggingface.co/onnx-community/nanoLLaVA-1.5/resolve/main/onnx/vision_encoder_quantized.onnx
- Command line
-
hf download hf://onnx-community/nanoLLaVA-1.5/onnx/vision_encoder_quantized.onnx
-
curl -L -o vision_encoder_quantized.onnx https://huggingface.co/onnx-community/nanoLLaVA-1.5/resolve/main/onnx/vision_encoder_quantized.onnx
405 MB
- Xet hash:
- fb6984be6e662d28ee838ea23096d5da069b73c0fd26a409d8672ac86aa49be0
- Size of remote file:
- 405 MB
- SHA256:
- eab5b92a6e26ae213dd69c9d1bf7a9cda3b42681649ceb775b588b8afca08ef0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.