Update README.md
Browse files
README.md
CHANGED
|
@@ -60,7 +60,7 @@ Idefics3 demonstrates a net improvement over Idefics2, especially in document un
|
|
| 60 |
| **Idefics3-8B** | 46.6 | 58.4 | 55.9 | 87.7 | 74.9 |
|
| 61 |
|
| 62 |
|
| 63 |
-
**
|
| 64 |
- We use 169 visual tokens to encode a image of size 364x364. Each image is divided into several sub images of sizes at most 364x364, which are then encoded separately.
|
| 65 |
- For the fine-tuning datasets, we have extended [The Cauldron](https://huggingface.co/datasets/HuggingFaceM4/the_cauldron) and added several datasets, including [Docmatix](HuggingFaceM4/Docmatix). We will push soon these datasets to the same repo of The Cauldron (TODO).
|
| 66 |
|
|
|
|
| 60 |
| **Idefics3-8B** | 46.6 | 58.4 | 55.9 | 87.7 | 74.9 |
|
| 61 |
|
| 62 |
|
| 63 |
+
**Idefics3 introduces several changes compared to Idefics2:**
|
| 64 |
- We use 169 visual tokens to encode a image of size 364x364. Each image is divided into several sub images of sizes at most 364x364, which are then encoded separately.
|
| 65 |
- For the fine-tuning datasets, we have extended [The Cauldron](https://huggingface.co/datasets/HuggingFaceM4/the_cauldron) and added several datasets, including [Docmatix](HuggingFaceM4/Docmatix). We will push soon these datasets to the same repo of The Cauldron (TODO).
|
| 66 |
|