Update README.md

README.md

@@ -1,9 +1,38 @@
 ---
 license: mit
+datasets:
+- tyqiangz/multilingual-sentiments
+- cardiffnlp/tweet_sentiment_multilingual
+- mteb/tweet_sentiment_multilingual
+- Sp1786/multiclass-sentiment-analysis-dataset
+- stanfordnlp/sst2
+language:
+- en
+- de
+- es
+- fr
+- ja
+- zh
+- id
+- ar
+- hi
+- it
+- ms
+- pt
+metrics:
+- accuracy
+- f1
+base_model:
+- microsoft/deberta-v3-base
+tags:
+- sentiment
 ---
 
 # Model 
-Multi-language sentiment classification model developed over the Microsoft [DeBERTa-v3 base model](https://huggingface.co/microsoft/deberta-v3-base). In order to train the model the following dataset where used:
+
+Multi-language sentiment classification model developed over the Microsoft [DeBERTa-v3 base model](https://huggingface.co/microsoft/deberta-v3-base). 
+Model where trained on mulitple datasets with multiple languages with additional weights over class (sentiment categories: Negative, Positive, Neutral).
+In order to train the model the following dataset where used:
  - tyqiangz/multilingual-sentiments
  - cardiffnlp/tweet_sentiment_multilingual
  - mteb/tweet_sentiment_multilingual
@@ -32,5 +61,5 @@ Multi-language sentiment classification model developed over the Microsoft [DeBE
 | **amazon-var**   | Our    | 0.6432 | 0.9647   |
 |                  | GPT-4  | 0.0000 | 0.9450   |
 
-# Reference 
-TBA
+# Source code
+[Repo](https://github.com/alexdrk14/DeBerta-v3-base-Sent)