Image-Text-to-Text
Transformers.js
ONNX
English
lfm2_vl
vision-language
earth-observation
sentinel-2
galamsey
illegal-mining
lfm2-vl
lfm2.5-vl
object-detection
grounding
webgpu
conversational
Instructions to use samwell/galamsey-v9-e3-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use samwell/galamsey-v9-e3-onnx with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('image-text-to-text', 'samwell/galamsey-v9-e3-onnx');
| { | |
| "image_processor": { | |
| "data_format": "channels_first", | |
| "do_image_splitting": true, | |
| "do_normalize": true, | |
| "do_pad": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "downsample_factor": 2, | |
| "encoder_patch_size": 16, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "Lfm2VlImageProcessorFast", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "max_image_tokens": 256, | |
| "max_num_patches": 1024, | |
| "max_pixels_tolerance": 2.0, | |
| "max_tiles": 10, | |
| "min_image_tokens": 64, | |
| "min_tiles": 2, | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_row_col_info": true, | |
| "size": { | |
| "height": 512, | |
| "width": 512 | |
| }, | |
| "tile_size": 512, | |
| "use_thumbnail": true | |
| }, | |
| "processor_class": "Lfm2VlProcessor" | |
| } | |