ShuxianZou
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -6,10 +6,20 @@ AIDO.RNA is a 1.6B parameter RNA foundation model trained on 42 million non-codi
|
|
6 |
</p>
|
7 |
|
8 |
## Model architectural details
|
9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
|
11 |
## Pre-training data
|
12 |
-
|
|
|
|
|
|
|
13 |
|
14 |
## Downstream evaluation
|
15 |
<p align="center">
|
|
|
6 |
</p>
|
7 |
|
8 |
## Model architectural details
|
9 |
+
AIDO.RNA is an encoder-only transformer and is pre-trained using masked language modeling (MLM) objective. The model architecture parameters are as follows:
|
10 |
+
| hyperparameter | value |
|
11 |
+
| :---: | :----: |
|
12 |
+
| num-layers | 32 |
|
13 |
+
| hidden-size | 2,048 |
|
14 |
+
| ffn-hidden-size | 5,440 |
|
15 |
+
| num-attn-heads | 32 |
|
16 |
+
|
17 |
|
18 |
## Pre-training data
|
19 |
+
The pre-training data contains 42 million unique ncRNA sequences from RNAcentral version 24.0.
|
20 |
+
<p align="center">
|
21 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/63008d4bc1e149ceaff724a3/EKvuUI9mBw5hkErzpXKm9.png" alt="description" style="width:100%; height:auto;">
|
22 |
+
</p>
|
23 |
|
24 |
## Downstream evaluation
|
25 |
<p align="center">
|