Update README.md

README.md

@@ -42,13 +42,12 @@ model-index:
 This model is a W.I.P
 
 ## Model description
-
-This model is a fine-tuned version of [KBLab/bart-base-swedish-cased](https://huggingface.co/KBLab/bart-base-swedish-cased) on the [Gabriel/bart-base-cnn-swe](https://huggingface.co/datasets/Gabriel/cnn_daily_swe) dataset.
+BART is a transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. BART is pre-trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text. This model is a fine-tuned version of [KBLab/bart-base-swedish-cased](https://huggingface.co/KBLab/bart-base-swedish-cased) on the [Gabriel/bart-base-cnn-swe](https://huggingface.co/datasets/Gabriel/cnn_daily_swe) dataset and can be used for summarization tasks.
 
 
 ## Intended uses & limitations
 
-This model should only be used to fine-tune further on.
+This model should only be used to fine-tune further on and summarization tasks.
 
 ## Training procedure