Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
hetzner
hetzner-gex44
hetzner-gpu
Instructions to use stefan-it/flair-co-funer-german_bert_base-bs8-e10-lr3e-05-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Flair
How to use stefan-it/flair-co-funer-german_bert_base-bs8-e10-lr3e-05-1 with Flair:
from flair.models import SequenceTagger tagger = SequenceTagger.load("stefan-it/flair-co-funer-german_bert_base-bs8-e10-lr3e-05-1") - Notebooks
- Google Colab
- Kaggle
readme: add dataset information to metadata (#2)
Browse files- readme: add dataset information to metadata (36f63997cc74023fa56433ff834c6f9b2971a04f)
README.md
CHANGED
|
@@ -9,6 +9,8 @@ tags:
|
|
| 9 |
- hetzner-gex44
|
| 10 |
- hetzner-gpu
|
| 11 |
base_model: google-bert/bert-base-german-cased
|
|
|
|
|
|
|
| 12 |
widget:
|
| 13 |
- text: Wesentliche Tätigkeiten der Compliance-Funktion wurden an die Mercurtainment
|
| 14 |
AG , Düsseldorf , ausgelagert .
|
|
@@ -40,7 +42,7 @@ fine-tuning.
|
|
| 40 |
A hyper-parameter search over the following parameters with 5 different seeds per configuration is performed:
|
| 41 |
|
| 42 |
* Batch Sizes: [`16`, `8`]
|
| 43 |
-
* Learning Rates: [`
|
| 44 |
|
| 45 |
More details can be found in this [repository](https://github.com/stefan-it/co-funer). All models are fine-tuned on a
|
| 46 |
[Hetzner GX44](https://www.hetzner.com/dedicated-rootserver/matrix-gpu/) with an NVIDIA RTX 4000.
|
|
|
|
| 9 |
- hetzner-gex44
|
| 10 |
- hetzner-gpu
|
| 11 |
base_model: google-bert/bert-base-german-cased
|
| 12 |
+
datasets:
|
| 13 |
+
- stefan-it/co-funer
|
| 14 |
widget:
|
| 15 |
- text: Wesentliche Tätigkeiten der Compliance-Funktion wurden an die Mercurtainment
|
| 16 |
AG , Düsseldorf , ausgelagert .
|
|
|
|
| 42 |
A hyper-parameter search over the following parameters with 5 different seeds per configuration is performed:
|
| 43 |
|
| 44 |
* Batch Sizes: [`16`, `8`]
|
| 45 |
+
* Learning Rates: [`5e-05`, `3e-05`]
|
| 46 |
|
| 47 |
More details can be found in this [repository](https://github.com/stefan-it/co-funer). All models are fine-tuned on a
|
| 48 |
[Hetzner GX44](https://www.hetzner.com/dedicated-rootserver/matrix-gpu/) with an NVIDIA RTX 4000.
|