Update README.md
Browse files
README.md
CHANGED
|
@@ -25,6 +25,12 @@ The model was developed within the [PoVeJMo](https://povejmo.si) research progra
|
|
| 25 |
- **Repository:** https://github.com/SloLama/NeMo
|
| 26 |
- **Paper:** https://www.sdjt.si/wp/wp-content/uploads/2024/09/JT-DH-2024_Vres_Bozic_Potocnik_Martincic_Robnik.pdf
|
| 27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
## How to Get Started with the Model
|
| 29 |
|
| 30 |
The inference can be done using the following snippet of code:
|
|
@@ -132,4 +138,6 @@ The model was evaluated using [Slovene SuperGLUE](https://slobench.cjvt.si/leade
|
|
| 132 |
| SlovenianGPT | **0.3805 ± 0.0142** | **0.6498 ± 0.0098** | 0.4523 ± 0.0087 | **0.4935 ± 0.0050** | **0.0432 ± 0.0034** | **0.27 ± 0.0199** | **0.6937 ± 0.0108** | **0.644 ± 0.0135** |
|
| 133 |
| SlovenianGPT-Chat* | 0.3567 ± 0.014 | 0.5901 ± 0.0101 | **0.4706 ± 0.0087** | 0.4719 ± 0.0050 | 0.0003 ± 0.0003 | **0.27 ± 0.0199** | 0.6861 ± 0.0108 | 0.6425 ± 0.0135 |
|
| 134 |
|
| 135 |
-
*SlovenianGPT-Chat was obtained by instruction-tuning Aleksa Gordić's [SlovenianGPT](https://huggingface.co/gordicaleksa/SlovenianGPT) on our instruction dataset.
|
|
|
|
|
|
|
|
|
| 25 |
- **Repository:** https://github.com/SloLama/NeMo
|
| 26 |
- **Paper:** https://www.sdjt.si/wp/wp-content/uploads/2024/09/JT-DH-2024_Vres_Bozic_Potocnik_Martincic_Robnik.pdf
|
| 27 |
|
| 28 |
+
## Intended usage
|
| 29 |
+
|
| 30 |
+
This version of the model is quite small and lacks instruction and safety tuning. Hence, using it as a general purpose model is **STRONGLY DISCOURAGED!!!** The model might also contain certain biases. We do not recommend usage of this model in any other language than Slovene.
|
| 31 |
+
|
| 32 |
+
The model can be efficiently tuned for specific use cases as suggested by promising results of fine-tuned models on SuperGLUE and SI-NLI benchmarks.
|
| 33 |
+
|
| 34 |
## How to Get Started with the Model
|
| 35 |
|
| 36 |
The inference can be done using the following snippet of code:
|
|
|
|
| 138 |
| SlovenianGPT | **0.3805 ± 0.0142** | **0.6498 ± 0.0098** | 0.4523 ± 0.0087 | **0.4935 ± 0.0050** | **0.0432 ± 0.0034** | **0.27 ± 0.0199** | **0.6937 ± 0.0108** | **0.644 ± 0.0135** |
|
| 139 |
| SlovenianGPT-Chat* | 0.3567 ± 0.014 | 0.5901 ± 0.0101 | **0.4706 ± 0.0087** | 0.4719 ± 0.0050 | 0.0003 ± 0.0003 | **0.27 ± 0.0199** | 0.6861 ± 0.0108 | 0.6425 ± 0.0135 |
|
| 140 |
|
| 141 |
+
*SlovenianGPT-Chat was obtained by instruction-tuning Aleksa Gordić's [SlovenianGPT](https://huggingface.co/gordicaleksa/SlovenianGPT) on our instruction dataset.
|
| 142 |
+
|
| 143 |
+
|