Video-Text-to-Text
Transformers
Safetensors
qwen3_vl
image-text-to-text
camera-movement
video-understanding
qwen3-vl
vggt-injection
Instructions to use ddz16/CamInject-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ddz16/CamInject-4B with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("ddz16/CamInject-4B") model = AutoModelForMultimodalLM.from_pretrained("ddz16/CamInject-4B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
rename model_type: vggt_direct -> caminject
Browse files
args.json
CHANGED
|
@@ -202,7 +202,7 @@
|
|
| 202 |
"ray_exp_name": null,
|
| 203 |
"device_groups": null,
|
| 204 |
"model": "Qwen/Qwen3-VL-4B-Instruct",
|
| 205 |
-
"model_type": "
|
| 206 |
"model_revision": null,
|
| 207 |
"task_type": "causal_lm",
|
| 208 |
"torch_dtype": "bfloat16",
|
|
|
|
| 202 |
"ray_exp_name": null,
|
| 203 |
"device_groups": null,
|
| 204 |
"model": "Qwen/Qwen3-VL-4B-Instruct",
|
| 205 |
+
"model_type": "qwen3_vl_caminject",
|
| 206 |
"model_revision": null,
|
| 207 |
"task_type": "causal_lm",
|
| 208 |
"torch_dtype": "bfloat16",
|