Update README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ pipeline_tag: text-generation
|
|
| 15 |
---
|
| 16 |
[](https://doi.org/10.5281/zenodo.17120223)
|
| 17 |
|
| 18 |
-
# Kren v1:
|
| 19 |
|
| 20 |
Kren v1 is the first *publicly documented* encoder→decoder conversion producing a generative language model for an Indian language (Khasi). The conversion was performed by transferring weights and adapting the architecture of MWirelabs/khasibert (RoBERTa-style encoder) into a GPT-2 style causal decoder, followed by progressive causal LM fine-tuning.
|
| 21 |
|
|
|
|
| 15 |
---
|
| 16 |
[](https://doi.org/10.5281/zenodo.17120223)
|
| 17 |
|
| 18 |
+
# Kren v1: Khasi Generative Language Model
|
| 19 |
|
| 20 |
Kren v1 is the first *publicly documented* encoder→decoder conversion producing a generative language model for an Indian language (Khasi). The conversion was performed by transferring weights and adapting the architecture of MWirelabs/khasibert (RoBERTa-style encoder) into a GPT-2 style causal decoder, followed by progressive causal LM fine-tuning.
|
| 21 |
|