Image-Text-to-Text
Transformers.js
ONNX
qwen3_vl
webgpu
interpretability
attention-steering
conversational
Instructions to use baulab/Qwen3-VL-2B-Instruct-GazeHeads-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use baulab/Qwen3-VL-2B-Instruct-GazeHeads-ONNX with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('image-text-to-text', 'baulab/Qwen3-VL-2B-Instruct-GazeHeads-ONNX');
gaze-head steering ONNX build (decomposed attention in gaze layers, stub vision encoder)
9316761 verified | { | |
| "size": { | |
| "longest_edge": 16777216, | |
| "shortest_edge": 65536 | |
| }, | |
| "patch_size": 16, | |
| "temporal_patch_size": 2, | |
| "merge_size": 2, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "processor_class": "Qwen3VLProcessor", | |
| "image_processor_type": "Qwen2VLImageProcessorFast" | |
| } |