Update README.md
Browse files
README.md
CHANGED
|
@@ -19,11 +19,13 @@ Cephalo provides a robust framework for multimodal interaction and understanding
|
|
| 19 |
## Overview of Models:
|
| 20 |
|
| 21 |
- Item 1 [Cephalo-Phi-3-vision-128k-4b-alpha](https://huggingface.co/lamm-mit/Cephalo-Phi-3-vision-128k-4b-alpha)
|
|
|
|
| 22 |
- Item 2 [Cephalo-Phi-3-vision-128k-4b-beta](https://huggingface.co/lamm-mit/Cephalo-Phi-3-vision-128k-4b-beta)
|
|
|
|
| 23 |
- Item 3 [Cephalo-Idefics-2-vision-8b-alpha](https://huggingface.co/lamm-mit/Cephalo-Idefics-2-vision-8b-alpha)
|
|
|
|
| 24 |
- Item 3 [Cephalo-Idefics-2-vision-8b-beta](https://huggingface.co/lamm-mit/Cephalo-Idefics-2-vision-8b-beta)
|
| 25 |
-
-
|
| 26 |
-
-
|
| 27 |
|
| 28 |
## Citation
|
| 29 |
|
|
|
|
| 19 |
## Overview of Models:
|
| 20 |
|
| 21 |
- Item 1 [Cephalo-Phi-3-vision-128k-4b-alpha](https://huggingface.co/lamm-mit/Cephalo-Phi-3-vision-128k-4b-alpha)
|
| 22 |
+
- Base version of the Cephalo-Phi-3 model, trained on GPT-4o distilled image-text data from Wikipedia and scientific papers
|
| 23 |
- Item 2 [Cephalo-Phi-3-vision-128k-4b-beta](https://huggingface.co/lamm-mit/Cephalo-Phi-3-vision-128k-4b-beta)
|
| 24 |
+
- Improved version of the Cephalo-Phi-3 model, trained on GPT-4o and Idefics-2 distilled image-text data from Wikipedia and scientific papers, as well as a large text-only corpus
|
| 25 |
- Item 3 [Cephalo-Idefics-2-vision-8b-alpha](https://huggingface.co/lamm-mit/Cephalo-Idefics-2-vision-8b-alpha)
|
| 26 |
+
- Trained on Idefics-2 distilled image-text data from Wikipedia and scientific papers
|
| 27 |
- Item 3 [Cephalo-Idefics-2-vision-8b-beta](https://huggingface.co/lamm-mit/Cephalo-Idefics-2-vision-8b-beta)
|
| 28 |
+
- Trained on GPT-4o distilled image-text data from Wikipedia and scientific papers
|
|
|
|
| 29 |
|
| 30 |
## Citation
|
| 31 |
|