Image-to-Text
Transformers
Safetensors
PEFT
English
vision-language
image-captioning
SmolVLM
LoRA
QLoRA
COCO
accelerate
Instructions to use Amirhossein75/VLM-Image-Captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Amirhossein75/VLM-Image-Captioning 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="Amirhossein75/VLM-Image-Captioning")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Amirhossein75/VLM-Image-Captioning", dtype="auto") - PEFT
How to use Amirhossein75/VLM-Image-Captioning with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -188,7 +188,7 @@ python train_vlm_sft.py \
|
|
| 188 |
---
|
| 189 |
|
| 190 |
## Evaluation
|
| 191 |
-
### 📊 Score card
|
| 192 |
|
| 193 |
**All scores increase with higher values (↑).** For visualization, `CIDEr` is shown ×100 in the chart to match the 0–100 scale of other metrics.
|
| 194 |
|
|
|
|
| 188 |
---
|
| 189 |
|
| 190 |
## Evaluation
|
| 191 |
+
### 📊 Score card(on subsample of main data)
|
| 192 |
|
| 193 |
**All scores increase with higher values (↑).** For visualization, `CIDEr` is shown ×100 in the chart to match the 0–100 scale of other metrics.
|
| 194 |
|