Image-to-Text
Transformers
pixeltext
feature-extraction
ocr
vision-language
paligemma
custom-model
text-extraction
document-ai
multi-language
custom_code
Instructions to use BabaK07/pixeltext-ai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BabaK07/pixeltext-ai 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="BabaK07/pixeltext-ai", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("BabaK07/pixeltext-ai", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Optimize config for safetensors loading
Browse files- config.json +1 -0
config.json
CHANGED
|
@@ -8,6 +8,7 @@
|
|
| 8 |
"vocab_size": 257216,
|
| 9 |
"torch_dtype": "float32",
|
| 10 |
"transformers_version": "4.40.0",
|
|
|
|
| 11 |
"auto_map": {
|
| 12 |
"AutoModel": "modeling_pixeltext.FixedPixelTextOCR",
|
| 13 |
"AutoConfig": "modeling_pixeltext.PixelTextConfig"
|
|
|
|
| 8 |
"vocab_size": 257216,
|
| 9 |
"torch_dtype": "float32",
|
| 10 |
"transformers_version": "4.40.0",
|
| 11 |
+
"use_safetensors": true,
|
| 12 |
"auto_map": {
|
| 13 |
"AutoModel": "modeling_pixeltext.FixedPixelTextOCR",
|
| 14 |
"AutoConfig": "modeling_pixeltext.PixelTextConfig"
|