Update README.md
Browse files
README.md
CHANGED
|
@@ -35,6 +35,8 @@ datasets:
|
|
| 35 |
5. **Built on Qwen2.5-VL Architecture**: Leverages the strengths of the 3B multimodal instruction-tuned variant for fine-grained reasoning.
|
| 36 |
6. **Multilingual Capability**: English is default, with multilingual captioning enabled through prompt engineering.
|
| 37 |
|
|
|
|
|
|
|
| 38 |
# Training Details
|
| 39 |
|
| 40 |
This model was fine-tuned on a mixture of curated image–caption datasets with emphasis on **attribute-based captioning** and **precise object-property definition**:
|
|
|
|
| 35 |
5. **Built on Qwen2.5-VL Architecture**: Leverages the strengths of the 3B multimodal instruction-tuned variant for fine-grained reasoning.
|
| 36 |
6. **Multilingual Capability**: English is default, with multilingual captioning enabled through prompt engineering.
|
| 37 |
|
| 38 |
+
> model type: experimental
|
| 39 |
+
|
| 40 |
# Training Details
|
| 41 |
|
| 42 |
This model was fine-tuned on a mixture of curated image–caption datasets with emphasis on **attribute-based captioning** and **precise object-property definition**:
|