Update README.md
Browse files
README.md
CHANGED
@@ -28,9 +28,11 @@ tags:
|
|
28 |
|
29 |
> The **Inkscope-Captions-2B-0526** model is a fine-tuned version of *Qwen2-VL-2B-Instruct*, optimized for **image captioning**, **vision-language understanding**, and **English-language caption generation**. This model was fine-tuned on the `conceptual-captions-cc12m-llavanext` dataset (first 30k entries) to generate **detailed, high-quality captions** for images, including complex or abstract scenes.
|
30 |
|
31 |
-
> [!
|
32 |
Colab Demo : https://huggingface.co/prithivMLmods/Inkscope-Captions-2B-0526/blob/main/Inkscope%20Captions%202B%200526%20Demo/Inkscope-Captions-2B-0526.ipynb
|
33 |
|
|
|
|
|
34 |
---
|
35 |
|
36 |
#### Key Enhancements:
|
@@ -115,6 +117,12 @@ for new_text in streamer:
|
|
115 |
|
116 |

|
117 |

|
|
|
|
|
|
|
|
|
|
|
|
|
118 |
|
119 |
---
|
120 |
|
|
|
28 |
|
29 |
> The **Inkscope-Captions-2B-0526** model is a fine-tuned version of *Qwen2-VL-2B-Instruct*, optimized for **image captioning**, **vision-language understanding**, and **English-language caption generation**. This model was fine-tuned on the `conceptual-captions-cc12m-llavanext` dataset (first 30k entries) to generate **detailed, high-quality captions** for images, including complex or abstract scenes.
|
30 |
|
31 |
+
> [!note]
|
32 |
Colab Demo : https://huggingface.co/prithivMLmods/Inkscope-Captions-2B-0526/blob/main/Inkscope%20Captions%202B%200526%20Demo/Inkscope-Captions-2B-0526.ipynb
|
33 |
|
34 |
+
> [!note]
|
35 |
+
Video Understanding Demo : https://huggingface.co/prithivMLmods/Inkscope-Captions-2B-0526/blob/main/Inkscope-Captions-2B-0526-Video-Understanding/Inkscope-Captions-2B-0526-Video-Understanding.ipynb
|
36 |
---
|
37 |
|
38 |
#### Key Enhancements:
|
|
|
117 |
|
118 |

|
119 |

|
120 |
+
|
121 |
+
---
|
122 |
+
|
123 |
+
### **Video Inference**
|
124 |
+
|
125 |
+

|
126 |
|
127 |
---
|
128 |
|