Update README.md

README.md

@@ -14,19 +14,31 @@ should probably proofread and complete it, then remove this comment. -->
 
 # yoruba-diacritics-quantized
 
-This model is a fine-tuned version of [Davlan/mT5_base_yoruba_adr](https://huggingface.co/Davlan/mT5_base_yoruba_adr) on an unknown dataset.
+This model is a fine-tuned version of [Davlan/mT5_base_yoruba_adr](https://huggingface.co/Davlan/mT5_base_yoruba_adr) on a version of [Niger-Volta-LTI](https://github.com/Niger-Volta-LTI/yoruba-adr), provided by Bunmie-e on [huggingface](https://huggingface.co/datasets/bumie-e/Yoruba-diacritics-vs-non-diacritics).
 
 ## Model description
 
-More information needed
+The fine-tuning was performed using the PEFT-LoRa technique, aiming to improve the model's performance on tasks like diacritization restoration and generation.
+
+## Key Features:
+
+- **Base model:** `mT5_base_yoruba_adr` pre-trained on Yoruba text
+- **Fine-tuned dataset:** Yoruba diacritics dataset from `bumie-e/Yoruba-diacritics-vs-non-diacritics`
+- **Fine-tuning technique:** PEFT-LoRa
+
+## Potential Applications:
+
+- Diacritization restoration in Yoruba text
+- Generation of Yoruba text with correct diacritics
+- Natural language processing tasks for Yoruba language
 
 ## Intended uses & limitations
 
-More information needed
+More information coming
 
 ## Training and evaluation data
 
-More information needed
+More information coming 
 
 ## Training procedure
 
@@ -47,7 +59,7 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-
+coming soon.
 
 ### Framework versions