Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,8 @@ license: apache-2.0
|
|
| 4 |
|
| 5 |
This is a checkpoint of a fine tune of BART to act as an autoencoder with fixed-size 32x64 latent space, to be used for training diffusion models. See https://arxiv.org/abs/2212.09462
|
| 6 |
|
|
|
|
|
|
|
| 7 |
trained from https://github.com/bary12/latent-diffusion-for-language using the following command
|
| 8 |
|
| 9 |
```
|
|
|
|
| 4 |
|
| 5 |
This is a checkpoint of a fine tune of BART to act as an autoencoder with fixed-size 32x64 latent space, to be used for training diffusion models. See https://arxiv.org/abs/2212.09462
|
| 6 |
|
| 7 |
+
even though this was trained for less than in the paper and on a more diverse dataset, it's pretty good with a validation loss of 0.14, and the reconstruction is correct >90% of the time.
|
| 8 |
+
|
| 9 |
trained from https://github.com/bary12/latent-diffusion-for-language using the following command
|
| 10 |
|
| 11 |
```
|