Commit
•
3fc7f21
1
Parent(s):
73a98a0
Update README.md
Browse files
README.md
CHANGED
@@ -1,9 +1,7 @@
|
|
1 |
---
|
2 |
license: gemma
|
3 |
-
datasets:
|
4 |
-
- ai4privacy/pii-masking-65k
|
5 |
language:
|
6 |
-
- no
|
7 |
---
|
8 |
|
9 |
# PIIMask-NOR Model
|
@@ -14,7 +12,6 @@ The PIIMask-NOR model is a specialized language model fine-tuned for the task of
|
|
14 |
|
15 |
- **Model Name:** PIIMask-NOR
|
16 |
- **Base Model:** [google/gemma-1.1-2b-it](https://huggingface.co/google/gemma-1.1-2b-it)
|
17 |
-
- **Fine-tuning Dataset:** [ai4privacy/pii-masking-65k](https://huggingface.co/datasets/ai4privacy/pii-masking-65k) (machine translated into Norwegian, Bokmål)
|
18 |
- **Quantization:** 4-bit quantization using NF4 with double quantization and float16 compute dtype.
|
19 |
- **Training Steps:** The model checkpoints are available at 1, 2, 3, and 4 epochs.
|
20 |
|
@@ -101,4 +98,4 @@ This model is a derivative of the "google/gemma-1.1-2b-it" model and complies wi
|
|
101 |
|
102 |
## License
|
103 |
|
104 |
-
The PIIMask-NOR model is distributed under the same terms as the base model. For more details, please refer to the [Gemma Terms of Use](https://ai.google.dev/gemma/terms).
|
|
|
1 |
---
|
2 |
license: gemma
|
|
|
|
|
3 |
language:
|
4 |
+
- 'no'
|
5 |
---
|
6 |
|
7 |
# PIIMask-NOR Model
|
|
|
12 |
|
13 |
- **Model Name:** PIIMask-NOR
|
14 |
- **Base Model:** [google/gemma-1.1-2b-it](https://huggingface.co/google/gemma-1.1-2b-it)
|
|
|
15 |
- **Quantization:** 4-bit quantization using NF4 with double quantization and float16 compute dtype.
|
16 |
- **Training Steps:** The model checkpoints are available at 1, 2, 3, and 4 epochs.
|
17 |
|
|
|
98 |
|
99 |
## License
|
100 |
|
101 |
+
The PIIMask-NOR model is distributed under the same terms as the base model. For more details, please refer to the [Gemma Terms of Use](https://ai.google.dev/gemma/terms).
|