Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
**Where to send questions or comments about the model:**
|
| 3 |
+
https://github.com/LargeWorldModel/lwm/issues
|
| 4 |
+
|
| 5 |
+
## Training dataset
|
| 6 |
+
- Books3 dataset
|
| 7 |
+
- 700B text-image pairs from Laion-2B-en, filtered to only keep images with at least 256 resolution
|
| 8 |
+
- 400M text-image pairs from COYO-700M, filtered to only keep images with at least 256 resolution
|
| 9 |
+
- 10M text-video pairs from WebVid10M
|
| 10 |
+
- 3M text-video pairs from a subset of InternVid10M
|
| 11 |
+
- 73K text-video chat pairs from Valley-Instruct-73K
|
| 12 |
+
- 100K text-video chat pairs from Video-ChatGPT
|