Update README.md
Browse files
README.md
CHANGED
|
@@ -2,11 +2,12 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
Pretrained toy model. Made with Andrej Karpathy's NanoGPT, ~2023.
|
|
|
|
| 5 |
Parameters:
|
| 6 |
-
batch_size = 64
|
| 7 |
-
block_size = 256
|
| 8 |
-
n_layer = 8
|
| 9 |
-
n_head = 8
|
| 10 |
-
n_embd = 768
|
| 11 |
|
| 12 |
Everything else is left as is.
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
Pretrained toy model. Made with Andrej Karpathy's NanoGPT, ~2023.
|
| 5 |
+
|
| 6 |
Parameters:
|
| 7 |
+
* batch_size = 64
|
| 8 |
+
* block_size = 256
|
| 9 |
+
* n_layer = 8
|
| 10 |
+
* n_head = 8
|
| 11 |
+
* n_embd = 768
|
| 12 |
|
| 13 |
Everything else is left as is.
|