Describe limitations
Browse files
README.md
CHANGED
@@ -7,7 +7,9 @@ datasets:
|
|
7 |
- laion/laion_100m_vqgan_f8
|
8 |
---
|
9 |
|
10 |
-
This model is collaboratively
|
|
|
|
|
11 |
|
12 |
# Model Description
|
13 |
|
@@ -19,8 +21,12 @@ You can check our [dashboard](https://huggingface.co/spaces/training-transformer
|
|
19 |
|
20 |
# How to Use
|
21 |
|
22 |
-
|
23 |
|
24 |
# Limitations
|
25 |
|
26 |
-
This model is
|
|
|
|
|
|
|
|
|
|
7 |
- laion/laion_100m_vqgan_f8
|
8 |
---
|
9 |
|
10 |
+
This model is trained collaboratively — it is a part of the NeurIPS 2021 demonstration ["Training Transformers Together"](https://training-transformers-together.github.io/).
|
11 |
+
|
12 |
+
The latest model checkpoint will be uploaded to this repository every 6 hours until the training stops.
|
13 |
|
14 |
# Model Description
|
15 |
|
|
|
21 |
|
22 |
# How to Use
|
23 |
|
24 |
+
You can start from our [Colab notebook for running inference](https://colab.research.google.com/drive/1Vkb-4nhEEH1a5vrKtpL4MTNiUTPdpPUl?usp=sharing).
|
25 |
|
26 |
# Limitations
|
27 |
|
28 |
+
This model is created only as a demonstration of the new distributed training methods. **It should not be used for anything besides research purposes.**
|
29 |
+
|
30 |
+
The authors have done only the most basic dataset filtering, so the model may be susceptible to biases in the training data and/or generate inappropriate content.
|
31 |
+
|
32 |
+
At the moment, the model's generative capabilities are limited due to the absence of extensive experiments with the architecture and incomplete training.
|