Create README.md
Browse files
README.md
CHANGED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags: [Danish, Mixed Tokenization, CerebrasGPT]
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
### DA-MIXED-CEREBRAS
|
| 7 |
+
|
| 8 |
+
This is an experimental Danish language model fine-tuned on a combination of tokenizers, including both morphological and BPE approaches. Built on the CerebrasGPT-111M architecture, it explores how mixed tokenization strategies affect Danish text generation.
|