Create README.md

README.md

@@ -0,0 +1,45 @@
+---
+language: 
+  - en
+tags:
+- Sentence Similarity
+- Pytorch
+- Sentence Transformers
+- Transformers
+license: "apache-2.0"
+---
+
+# Twitter4SSE
+
+This model maps texts to 768 dimensional dense embeddings that encode semantic similarity. 
+It was trained with Multiple Negatives Ranking Loss (MNRL) on a Twitter dataset. 
+It was initialized from [BERTweet](https://huggingface.co/vinai/bertweet-base) and trained with [Sentence-transformers](https://www.sbert.net/). 
+
+## Usage
+
+The model is easier to use with sentence-trainsformers library
+
+```
+pip install -U sentence-transformers
+```
+
+```
+from sentence_transformers import SentenceTransformer
+sentences = ["This is the first tweet", "This is the second tweet"]
+
+model = SentenceTransformer('digio/Twitter4SSE')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+Without sentence-transfomer library, please refer to [this repository](https://huggingface.co/sentence-transformers) for detailed instructions on how to use Sentence Transformers on Huggingface. 
+
+## Citing & Authors
+
+The official paper "Exploiting Twitter as Source of Large Corpora of Weakly Similar Pairs for Semantic Sentence Embeddings" will be presented at EMNLP 2021. Further details will be available soon. 
+
+The official code is available on [GitHub](https://github.com/marco-digio/Twitter4SSE)
+
+
+The model cards have a YAML section that specify metadata. These are the fields