Feature Extraction
Transformers
Safetensors
jolia
medical
radiology
ct
3d
vision
foundation-model
self-supervised
custom_code
Instructions to use raidium/Jolia with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use raidium/Jolia with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="raidium/Jolia", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("raidium/Jolia", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,8 +21,6 @@ program. It encodes a whole 3D CT volume into:
|
|
| 21 |
- **per-organ embeddings** — 102 named organ slots produced by organ-query
|
| 22 |
cross-attention pooling, trained to align with per-organ report text.
|
| 23 |
|
| 24 |
-
> ⚠️ Research preview. Not a medical device; not for clinical use.
|
| 25 |
-
|
| 26 |
## Installation
|
| 27 |
|
| 28 |
```bash
|
|
@@ -107,6 +105,8 @@ padding. Methods like `encode_organs` expose only the named slots.
|
|
| 107 |
|
| 108 |
## Intended use & limitations
|
| 109 |
|
|
|
|
|
|
|
| 110 |
Jolia is a **feature extractor** for downstream radiology tasks (classification,
|
| 111 |
retrieval, per-organ analysis) via linear probing or fine-tuning. It is trained
|
| 112 |
on adult chest/abdominal CT and will not generalize to other modalities or
|
|
|
|
| 21 |
- **per-organ embeddings** — 102 named organ slots produced by organ-query
|
| 22 |
cross-attention pooling, trained to align with per-organ report text.
|
| 23 |
|
|
|
|
|
|
|
| 24 |
## Installation
|
| 25 |
|
| 26 |
```bash
|
|
|
|
| 105 |
|
| 106 |
## Intended use & limitations
|
| 107 |
|
| 108 |
+
> ⚠️ Research preview. Not a medical device; not for clinical use.
|
| 109 |
+
|
| 110 |
Jolia is a **feature extractor** for downstream radiology tasks (classification,
|
| 111 |
retrieval, per-organ analysis) via linear probing or fine-tuning. It is trained
|
| 112 |
on adult chest/abdominal CT and will not generalize to other modalities or
|