Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,9 @@ license: apache-2.0
|
|
| 21 |
|
| 22 |
BübleLM is a German language model based on Gemma-2-2B, adapted using [trans-tokenization](https://pieter.ai/trans-tokenization/) with a custom German SentencePiece tokenizer. The model demonstrates how language-specific tokenization can significantly improve performance while maintaining the base model's capabilities.
|
| 23 |
|
|
|
|
|
|
|
|
|
|
| 24 |
## Model Details
|
| 25 |
|
| 26 |
- **Architecture**: Based on Gemma-2B decoder-only architecture
|
|
|
|
| 21 |
|
| 22 |
BübleLM is a German language model based on Gemma-2-2B, adapted using [trans-tokenization](https://pieter.ai/trans-tokenization/) with a custom German SentencePiece tokenizer. The model demonstrates how language-specific tokenization can significantly improve performance while maintaining the base model's capabilities.
|
| 23 |
|
| 24 |
+
This is an experimental version that received some finetuning using several german datasets.
|
| 25 |
+
DPO version will follow soon.
|
| 26 |
+
|
| 27 |
## Model Details
|
| 28 |
|
| 29 |
- **Architecture**: Based on Gemma-2B decoder-only architecture
|