Instructions to use vidore/colSmol-500M-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ColPali
How to use vidore/colSmol-500M-base with ColPali:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -58,7 +58,7 @@ from PIL import Image
|
|
| 58 |
from colpali_engine.models import ColIdefics3, ColIdefics3Processor
|
| 59 |
|
| 60 |
model = ColIdefics3.from_pretrained(
|
| 61 |
-
"vidore/
|
| 62 |
torch_dtype=torch.bfloat16,
|
| 63 |
device_map="cuda:0",
|
| 64 |
attn_implementation="flash_attention_2" # or eager
|
|
|
|
| 58 |
from colpali_engine.models import ColIdefics3, ColIdefics3Processor
|
| 59 |
|
| 60 |
model = ColIdefics3.from_pretrained(
|
| 61 |
+
"vidore/colSmol-500M-base",
|
| 62 |
torch_dtype=torch.bfloat16,
|
| 63 |
device_map="cuda:0",
|
| 64 |
attn_implementation="flash_attention_2" # or eager
|