Instructions to use microsoft/Magma-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/Magma-8B with Transformers:
# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("microsoft/Magma-8B", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update preprocessor_config.json
Browse files- preprocessor_config.json +4 -0
preprocessor_config.json
CHANGED
|
@@ -1,4 +1,8 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"anyres_strategy": "crop",
|
| 3 |
"base_img_size": 512,
|
| 4 |
"do_convert_rgb": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"auto_map": {
|
| 3 |
+
"AutoProcessor": "processing_magma.MagmaProcessor",
|
| 4 |
+
"AutoImageProcessor": "image_processing_magma.MagmaImageProcessor"
|
| 5 |
+
},
|
| 6 |
"anyres_strategy": "crop",
|
| 7 |
"base_img_size": 512,
|
| 8 |
"do_convert_rgb": true,
|