Datasets:
ArXiv:
License:
Update README.md
Browse files
README.md
CHANGED
|
@@ -154,9 +154,12 @@ During the training of **OS-Atlas-7B**, we randomly sampled predefined prompts t
|
|
| 154 |
Below is an example of a data entry:
|
| 155 |
|
| 156 |
```
|
| 157 |
-
"conversations": [{"from": "human", "value": "<image>\nUsing the provided screenshot, I'll describe webpage elements for you to locate (with bbox).\n<ref>media-maniacs.org</ref>\n<ref>Home</ref>\n<ref>Sitemap</ref>\n<ref>shop you can have what you choose 2012</ref>"},
|
|
|
|
| 158 |
```
|
| 159 |
|
|
|
|
|
|
|
| 160 |
***
|
| 161 |
|
| 162 |
**The following are the open-source datasets we used as data sources. We welcome everyone to check the details and cite these sources accordingly!**
|
|
|
|
| 154 |
Below is an example of a data entry:
|
| 155 |
|
| 156 |
```
|
| 157 |
+
"conversations": [{"from": "human", "value": "<image>\nUsing the provided screenshot, I'll describe webpage elements for you to locate (with bbox).\n<ref>media-maniacs.org</ref>\n<ref>Home</ref>\n<ref>Sitemap</ref>\n<ref>shop you can have what you choose 2012</ref>"},
|
| 158 |
+
{"from": "gpt", "value": "<ref>media-maniacs.org</ref><box>[[70,856,141,871]]</box>\n<ref>Home</ref><box>[[21,935,43,951]]</box>\n<ref>Sitemap</ref><box>[[21,919,52,934]]</box>\n<ref>shop you can have what you choose 2012</ref><box>[[368,839,523,855]]</box>"}]
|
| 159 |
```
|
| 160 |
|
| 161 |
+
The prompts we used are stored in `prompts.json`.
|
| 162 |
+
|
| 163 |
***
|
| 164 |
|
| 165 |
**The following are the open-source datasets we used as data sources. We welcome everyone to check the details and cite these sources accordingly!**
|