Instructions to use ddobokki/ko-trocr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ddobokki/ko-trocr with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="ddobokki/ko-trocr")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("ddobokki/ko-trocr") model = AutoModelForMultimodalLM.from_pretrained("ddobokki/ko-trocr", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Adding `safetensors` variant of this model
#1
by SFconvertbot - opened
- model.safetensors +3 -0
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87d271990e8227f9f518d0d349968feb15fc87066573cf7107d9b53c3ef8176a
|
| 3 |
+
size 427451424
|