Update README.md

README.md

@@ -8,20 +8,20 @@ tags:
 language:
 - de
 ---
-# {Overvie}
-Base-Model: gbert-base
+# {Overview}
+**Base-Model:** gbert-base
 
-Fine-Tuning: sentence-transformer
+**Fine-Tuning:** sentence-transformer
 
-Training data: german sts-dataset (can be found [here](https://github.com/t-systems-on-site-services-gmbh/german-STSbenchmark))
+**Training data:** german sts-dataset (can be found [here](https://github.com/t-systems-on-site-services-gmbh/german-STSbenchmark))
   * both aws und deepl machine translation are used
   * Training on sts-train, sts-dev
 
-Evaluation data: german sts-dataset (sts-test)
+**Evaluation data:** german sts-dataset (sts-test)
 
-Infrastructure: GPU V100 (20GB)
+**Infrastructure:** GPU V100 (20GB)
 
-Hyperparameter:
+**Hyperparameter:**
   * batch size 64
   * epochs 4
   * MultiNegativeRankingLoss
@@ -72,8 +72,8 @@ def mean_pooling(model_output, attention_mask):
 sentences = ['This is an example sentence', 'Each sentence is converted']
 
 # Load model from HuggingFace Hub
-tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
-model = AutoModel.from_pretrained('{MODEL_NAME}')
+tokenizer = AutoTokenizer.from_pretrained('{JoBeer/german-semantic-base}')
+model = AutoModel.from_pretrained('{JoBeer/german-semantic-base}')
 
 # Tokenize sentences
 encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
@@ -95,7 +95,7 @@ print(sentence_embeddings)
 
 <!--- Describe how your model was evaluated -->
 
-For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={JoBeer/german-semantic-base})
 
 
 ## Training