Upload latest_main.tex with huggingface_hub

latest_main.tex

@@ -60,7 +60,7 @@ We fill this gap with the first comprehensive tokenizer benchmark for Moroccan D
 \item \textbf{Proposed improvement}: A concatenated architecture that trains separate per-script sub-tokenizers, reducing cross-script disparity by up to $4\times$
 \end{enumerate}
 
-Our key findings are threefold. First, Darija-specific tokenization dramatically improves compression: our 80K tokenizer achieves 34\% lower fertility than DarijaBERT at the same vocabulary size. Second, cross-script fairness is achievable for Darija: shared Unigram at 80K reaches $\Delta F$ = 0.015 (near-zero disparity), while concatenated architectures provide consistent fairness across all algorithms. Third, vocabulary size saturates early: moving from 32K to 110K yields only marginal gains, suggesting that 32K is sufficient for most Darija applications. All 40 configurations achieve $\geq$99\% exact reconstruction.
+Our key findings are threefold. First, Darija-specific tokenization dramatically improves compression: our 80K tokenizer achieves 33\% lower fertility than DarijaBERT at the same vocabulary size. Second, cross-script fairness is achievable for Darija: shared Unigram at 80K reaches $\Delta F$ = 0.015 (near-zero disparity), while concatenated architectures provide consistent fairness across all algorithms. Third, vocabulary size saturates early: moving from 32K to 110K yields only marginal gains, suggesting that 32K is sufficient for most Darija applications. All 40 configurations achieve $\geq$99\% exact reconstruction.
 
 
 \section{Methodology}