Zero-Shot Classification
Transformers
PyTorch
Safetensors
bert
text-classification
Inference Endpoints
saattrupdan commited on
Commit
ccd5201
1 Parent(s): 00128ab

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -7
README.md CHANGED
@@ -28,12 +28,6 @@ inference:
28
  hypothesis_template: "Dette eksempel handler om {}"
29
  ---
30
 
31
- # Model Details
32
-
33
- ## Model Description
34
-
35
- - **Resources for more information:** <https://github.com/alexandrainst/ScandiNLI>
36
-
37
  # ScandiNLI - Natural Language Inference model for Scandinavian Languages
38
 
39
  This model is a fine-tuned version of [NbAiLab/nb-bert-base](https://huggingface.co/NbAiLab/nb-bert-base) for Natural Language Inference in Danish, Norwegian Bokmål and Swedish.
@@ -154,7 +148,7 @@ The training split of DanFEVER is generated using [this gist](https://gist.githu
154
 
155
  The three languages are sampled equally during training, and they're validated on validation splits of [DanFEVER](https://aclanthology.org/2021.nodalida-main.pdf#page=439) and machine translated versions of [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) for Swedish and Norwegian Bokmål, sampled equally.
156
 
157
- The full training logs can be found in [this Weights and Biases report](https://wandb.ai/saattrupdan/huggingface/reports/ScandiNLI--VmlldzozMDQyOTk1?accessToken=r9crgxqvvigy2hatdjeobzwipz7f3id5vqg8ooksljhfw6wl0hv1b05asypsfj9v).
158
 
159
  ### Training hyperparameters
160
 
 
28
  hypothesis_template: "Dette eksempel handler om {}"
29
  ---
30
 
 
 
 
 
 
 
31
  # ScandiNLI - Natural Language Inference model for Scandinavian Languages
32
 
33
  This model is a fine-tuned version of [NbAiLab/nb-bert-base](https://huggingface.co/NbAiLab/nb-bert-base) for Natural Language Inference in Danish, Norwegian Bokmål and Swedish.
 
148
 
149
  The three languages are sampled equally during training, and they're validated on validation splits of [DanFEVER](https://aclanthology.org/2021.nodalida-main.pdf#page=439) and machine translated versions of [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) for Swedish and Norwegian Bokmål, sampled equally.
150
 
151
+ Check out the [Github repository](https://github.com/alexandrainst/ScandiNLI) for the code used to train the ScandiNLI models, and the full training logs can be found in [this Weights and Biases report](https://wandb.ai/saattrupdan/huggingface/reports/ScandiNLI--VmlldzozMDQyOTk1?accessToken=r9crgxqvvigy2hatdjeobzwipz7f3id5vqg8ooksljhfw6wl0hv1b05asypsfj9v).
152
 
153
  ### Training hyperparameters
154