Update README.md

README.md

@@ -53,11 +53,11 @@ pipeline_tag: text-generation
 
 ## Model Description
 
-**SUHAIL-14B-preview** extends the open-weight **Qwen-3-14B-Base** to support Arabic instruction-following using **Low-Rank Adaptation (LoRA)**. LoRA introduces small trainable matrices to linear layers, keeping base weights frozen—enabling compact, efficient fine-tuning.
+**SUHAIL-14B-preview** extends the open-weight **Qwen-3-14B-Base** to better support Arabic instruction-following using **Low-Rank Adaptation (LoRA)**. LoRA introduces small trainable matrices to linear layers as well as attention layers, keeping base weights frozen—enabling compact, efficient fine-tuning. 
 
 ### 1 · Supervised Fine-Tuning (SFT)
 
-We first conducted SFT on a high-quality instruction dataset in Arabic and English. This dataset was curated using **Style-Aligned Response Ranking**, a RoBERTa-based reranker that filters out stylistically incoherent or low-quality samples from the Efficient Instruction-Tuning corpus. This step enhanced factuality and stylistic consistency.  
+We first conducted SFT on a high-quality instruction dataset in Arabic and English. This dataset was curated using **Style-Aligned Response Ranking**, a RoBERTa-based reranker that filters out stylistically incoherent or low-quality samples from the Instruction-Tuning corpus. This step enhanced factuality and stylistic consistency.  
 > **Result**: Up to 22% performance improvements observed on internal benchmarks (e.g., IFEVAL).
 
 ### 2 · Human Preference Alignment