Update README.md

README.md

@@ -17,8 +17,10 @@ library_name: peft
 
 # Model Card for SinLlama
 
-SinLlama is the first large language model specifically extended for Sinhala. It is based on Meta-Llama-3-8B and adapted through tokenizer vocabulary extension and continual pretraining on a 10M sentence Sinhala corpus. SinLlama significantly improves coverage and performance for Sinhala NLP tasks compared to base and instruct versions of Llama-3-8B. Note that this is a base model, which has NOT been instruct-tuned. So you still need to do task-specific fine-tuning.
+SinLlama is the first large language model specifically extended for Sinhala. It is based on Meta-Llama-3-8B and adapted through tokenizer vocabulary extension and continual pretraining on a 10M sentence Sinhala corpus. SinLlama significantly improves coverage and performance for Sinhala NLP tasks compared to base and instruct versions of Llama-3-8B. 
 
+*DISCLAIMER*
+This is a base model, which has NOT been instruct-tuned. So you still need to do task-specific fine-tuning.
 ---
 
 ## Model Details
@@ -50,13 +52,9 @@ Subsequent fine-tuning on Sinhala classification datasets (news categorization,
 
 ## Uses
 
-### Direct Use
-- Sinhala text generation
-- Sinhala text classification
-- Sentiment analysis, news categorization, and writing style classification
 
 ### Downstream Use
-- Instruction tuning for Sinhala dialogue systems
+- Instruction tuning for Sinhala dialogue systems, text classification, etc
 - Cross-lingual applications involving Sinhala
 - Educational and research applications in low-resource NLP
 
@@ -74,7 +72,7 @@ Subsequent fine-tuning on Sinhala classification datasets (news categorization,
 - **Risk:** Misuse in spreading misinformation or biased outputs in Sinhala.  
 
 ### Recommendations
-Users should carefully evaluate outputs before deployment, especially in sensitive or safety-critical applications. Fine-tuning with task/domain-specific Sinhala data is recommended for robustness.
+Users should carefully evaluate outputs before deployment, especially in sensitive or safety-critical applications. Fine-tuning with task/domain-specific Sinhala data is required for robustness.
 
 ---