Update README.md
Browse files
README.md
CHANGED
|
@@ -1,11 +1,3 @@
|
|
| 1 |
-
This model is trained from scratch using tokenized midi music.
|
| 2 |
-
I have trained a MidiTok tokeniser (REMI) and its made by spliting multi-track midi into a single track.
|
| 3 |
-
|
| 4 |
-
We then trained in on a small dataset.
|
| 5 |
-
Its using the Mistral model that has been cut down quite a bit.
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
---
|
| 10 |
license: mit
|
| 11 |
metrics:
|
|
@@ -16,4 +8,11 @@ tags:
|
|
| 16 |
- miditok
|
| 17 |
- music
|
| 18 |
- instrument
|
| 19 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
metrics:
|
|
|
|
| 8 |
- miditok
|
| 9 |
- music
|
| 10 |
- instrument
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
This model is trained from scratch using tokenized midi music.
|
| 15 |
+
I have trained a MidiTok tokeniser (REMI) and its made by spliting multi-track midi into a single track.
|
| 16 |
+
|
| 17 |
+
We then trained in on a small dataset.
|
| 18 |
+
Its using the Mistral model that has been cut down quite a bit.
|