Image-to-Text
Transformers.js
ONNX
English
multi_modality
webgpu
multimodal
text-to-image
vision-language
janus
browser-ai
edge-ai
Instructions to use Zhare-AI/janus-pro-7b-webgpu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use Zhare-AI/janus-pro-7b-webgpu with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('image-to-text', 'Zhare-AI/janus-pro-7b-webgpu');
| { | |
| "bos_token_id": 100000, | |
| "eos_token_id": 100001, | |
| "pad_token_id": 151643, | |
| "max_length": 2048, | |
| "max_new_tokens": 1024, | |
| "do_sample": true, | |
| "temperature": 0.7, | |
| "top_p": 0.9, | |
| "use_cache": true, | |
| "num_image_tokens": 576 | |
| } |