Any-to-Any
Transformers
Diffusers
Safetensors
English
llada2_moe
feature-extraction
multimodal
image-generation
image-understanding
image-editing
diffusion
Mixture of Experts
text-to-image
custom_code
Instructions to use inclusionAI/LLaDA2.0-Uni with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use inclusionAI/LLaDA2.0-Uni with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("inclusionAI/LLaDA2.0-Uni", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update image_tokenizer/preprocessor_config.json
Browse files
image_tokenizer/preprocessor_config.json
CHANGED
|
@@ -6,7 +6,7 @@
|
|
| 6 |
"do_resize": false,
|
| 7 |
"patch_size": 16,
|
| 8 |
"temporal_patch_size": 1,
|
| 9 |
-
"merge_size":
|
| 10 |
"image_mean": [0.5, 0.5, 0.5],
|
| 11 |
"image_std": [0.5, 0.5, 0.5],
|
| 12 |
"image_processor_type": "GlmImageImageProcessor",
|
|
|
|
| 6 |
"do_resize": false,
|
| 7 |
"patch_size": 16,
|
| 8 |
"temporal_patch_size": 1,
|
| 9 |
+
"merge_size": 1,
|
| 10 |
"image_mean": [0.5, 0.5, 0.5],
|
| 11 |
"image_std": [0.5, 0.5, 0.5],
|
| 12 |
"image_processor_type": "GlmImageImageProcessor",
|