Instructions to use daniel3303/PixtralGroundCap with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use daniel3303/PixtralGroundCap with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("mistral-community/pixtral-12b") model = PeftModel.from_pretrained(base_model, "daniel3303/PixtralGroundCap") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -56,9 +56,9 @@ model-index:
|
|
| 56 |
|
| 57 |
---
|
| 58 |
|
| 59 |
-
# Model Card for
|
| 60 |
|
| 61 |
-
This model is a fine-tuned version of Pixtral-12B
|
| 62 |
|
| 63 |
## Model Details
|
| 64 |
|
|
|
|
| 56 |
|
| 57 |
---
|
| 58 |
|
| 59 |
+
# Model Card for PixtralGroundCap
|
| 60 |
|
| 61 |
+
This model is a fine-tuned version of Pixtral-12B on the GroundCap dataset for grounded image captioning. It generates detailed image descriptions with explicit grounding tags that link textual descriptions to specific visual elements in the image. The model was trained on the GroundCap dataset and uses a novel tag system to ground objects (`<gdo>`), actions (`<gda>`), and locations (`<gdl>`) to specific regions in images.
|
| 62 |
|
| 63 |
## Model Details
|
| 64 |
|