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_q4f16.onnx from onnx-community/nanoLLaVA-1.5: direct link, hf CLI and curl.
- Browser
- Download file 229 MB
-
https://huggingface.co/onnx-community/nanoLLaVA-1.5/resolve/bbebb4745520963f1a3d1cfde885f6f778bc4bff/onnx/vision_encoder_q4f16.onnx
- Command line
-
hf download hf://onnx-community/nanoLLaVA-1.5@bbebb4745520963f1a3d1cfde885f6f778bc4bff/onnx/vision_encoder_q4f16.onnx
-
curl -L -o vision_encoder_q4f16.onnx https://huggingface.co/onnx-community/nanoLLaVA-1.5/resolve/bbebb4745520963f1a3d1cfde885f6f778bc4bff/onnx/vision_encoder_q4f16.onnx
229 MB
- Xet hash:
- 20b7409f1f2641afde44629f61faea602bbc8fce3ce59f38f7a1df3093b420da
- Size of remote file:
- 229 MB
- SHA256:
- 509d77f54c89bb4fddba679a0dc748e0b027843f6dd96e4243fde29b57895fa1
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.