Update README.md

README.md

@@ -1,7 +1,7 @@
 ---
 language: en
 datasets:
-- tweet-qa
+- tweet_qa
 tags:
 - qa
 
@@ -9,7 +9,7 @@ tags:
 
 
 # ByT5-base fine-tuned for Question Answering (on Tweets)
-[ByT5](https://huggingface.co/google/byt5-base) base fine-tuned on [tweets hate speech detection](https://huggingface.co/datasets/tweets_hate_speech_detection) dataset for **Sequence Classification** downstream task.
+[ByT5](https://huggingface.co/google/byt5-base) base fine-tuned on [TweetQA](https://huggingface.co/datasets/tweet_qa) dataset for **Question Answering** downstream task.
 
 # Details of ByT5 - Base 🧠
 
@@ -20,9 +20,9 @@ Paper: [ByT5: Towards a token-free future with pre-trained byte-to-byte models](
 Authors: *Linting Xue, Aditya Barua, Noah Constant, Rami Al-Rfou, Sharan Narang, Mihir Kale, Adam Roberts, Colin Raffel* 
 
 
-## Details of the downstream task (Sequence Classification as Text generation) - Dataset 📚
+## Details of the downstream task (Question Answering) - Dataset 📚
 
-[tweets_hate_speech_detection](hhttps://huggingface.co/datasets/tweets_hate_speech_detection)
+[TweetQA](hhttps://huggingface.co/datasets/tweets_hate_speech_detection)
 
 
 The objective of this task is to detect hate speech in tweets. For the sake of simplicity, we say a tweet contains hate speech if it has a racist or sexist sentiment associated with it. So, the task is to classify racist or sexist tweets from other tweets.