Update README.md

README.md

@@ -10,7 +10,7 @@ license: apache-2.0
 language:
 - am
 - ti
-
+This is a RoBERTa-base model trained on ~124M tweets from January 2018 to December 2021, and finetuned for sentiment analysis with the TweetEval benchmark. The original Twitter-based RoBERTa model can be found here and the original reference paper is TweetEval. This model is suitable for Amharic and Tigriyna.
 ---from transformers import XLMRobertaTokenizer, XLMRobertaForSequenceClassification
 model_name = "Hailay/FT_EXLMR"
 tokenizer = XLMRobertaTokenizer.from_pretrained(model_name)
@@ -22,7 +22,7 @@ outputs = model(**inputs)
 # Model Card for Model ID
 Model Card Summary: Hailay/FT_EXLMR
 Model Name: Hailay/FT_EXLMR
-Type: XLM-RoBERTa model for sequence classification
+Type: XLM-Roberta model for sequence classification
 Language(s): [Languages supported by the model]
 License: [License type, e.g., Apache 2.0]
 Pre-trained Model: xlm-roberta-base
@@ -35,13 +35,8 @@ Key Features:
 Trained Data: Custom dataset with text and labels
 Training Details: 3 epochs, learning rate of 1e-5
 Evaluation: Accuracy and loss metrics
-Getting Started:
-
 Code Example: Load the model and tokenizer, then use them for text classification.
 Considerations:
 
-Bias & Risks: Assess for biases; evaluate suitability for specific applications
-Environmental Impact: [Details about hardware and training time]
-Citation:
 
 BibTeX & APA formats available