Update README.md

README.md

@@ -5,14 +5,16 @@ tags:
 - feature-extraction
 - sentence-similarity
 - transformers
+- german
+- nli
+- text-classification
+
 
 ---
 
 # airnicco8/xlm-roberta-de
 
-This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
-
-<!--- Describe your model here -->
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. It is trained on the [Ted talks transcripts](https://www.kaggle.com/datasets/rounakbanik/ted-talks) filtered only by German language, the training setting is described [here](https://towardsdatascience.com/a-complete-guide-to-transfer-learning-from-english-to-other-languages-using-sentence-embeddings-8c427f8804a9). It can be used straight-forwardly for sentence similarity, but can also be fine-tuned for NLI and Text-Classification, examples coming soon.
 
 ## Usage (Sentence-Transformers)
 
@@ -26,7 +28,7 @@ Then you can use the model like this:
 
 ```python
 from sentence_transformers import SentenceTransformer
-sentences = ["This is an example sentence", "Each sentence is converted"]
+sentences = ["das ist eine glückliche Frau", "das ist ein glücklicher Mann", "das ist ein glücklicher Hund"]
 
 model = SentenceTransformer('airnicco8/xlm-roberta-de')
 embeddings = model.encode(sentences)
@@ -51,7 +53,7 @@ def mean_pooling(model_output, attention_mask):
 
 
 # Sentences we want sentence embeddings for
-sentences = ['This is an example sentence', 'Each sentence is converted']
+sentences = ["das ist eine glückliche Frau", "das ist ein glücklicher Mann", "das ist ein glücklicher Hund"]
 
 # Load model from HuggingFace Hub
 tokenizer = AutoTokenizer.from_pretrained('airnicco8/xlm-roberta-de')
@@ -87,7 +89,7 @@ The model was trained with the parameters:
 
 `torch.utils.data.dataloader.DataLoader` of length 3071 with parameters:
 ```
-{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
 ```
 
 **Loss**: