Add dataset info to benchmark results
Browse files
README.md
CHANGED
|
@@ -26,7 +26,7 @@ You'll generally want the "TE-only" .safetensors:
|
|
| 26 |
## The TEXT model has a modality gap of 0.80 (OpenAI pre-trained: 0.82).
|
| 27 |
- Trained with high temperature of 0.1 + tinkering.
|
| 28 |
- ImageNet/ObjectNet accuracy ~0.91 for both "SMOOTH" and "TEXT" models (pre-trained: ~0.84).
|
| 29 |
-
- The models (this plot = "TEXT" model) are also golden retrievers: 🥰🐕
|
| 30 |
|
| 31 |
|
| 32 |
|
|
|
|
| 26 |
## The TEXT model has a modality gap of 0.80 (OpenAI pre-trained: 0.82).
|
| 27 |
- Trained with high temperature of 0.1 + tinkering.
|
| 28 |
- ImageNet/ObjectNet accuracy ~0.91 for both "SMOOTH" and "TEXT" models (pre-trained: ~0.84).
|
| 29 |
+
- The models (this plot = "TEXT" model on MSCOCO) are also golden retrievers: 🥰🐕
|
| 30 |
|
| 31 |
|
| 32 |
|