Update README.md

README.md

@@ -34,7 +34,9 @@ This is a merge of pre-trained language models created using [mergekit](https://
 This model was merged using the [DaRE-Linear](https://developer.nvidia.com/blog/an-introduction-to-model-merging-for-llms/#:~:text=that%20did%20not.-,DARE,DARE%20derives%20from%20the%20following:) (Drop And REscal in Linear) merging methods, with [medalpaca-7b](https://huggingface.co/medalpaca/medalpaca-7b) as a base.
 
 * **DARE-Linear** (or DARE-Task Arithmetic) is the variant where the DARE-processed (sparsified and rescaled) delta parameters are merged using simple linear weighted averaging.
-* The final merged model is obtained by adding the weighted sum of the sparsified task vectors back to the base model:\(\theta _{merged}=\theta _{base}+\sum _{i=1}^{N}\alpha _{i}\cdot \^{\tau }_{i}\)where \(\^{\tau }_{i}\) are the DARE-processed task vectors and \(\alpha _{i}\) are the merging coefficients (weights) for each model. 
+* The final merged model is obtained by adding the weighted sum of the sparsified task vectors back to the base model:  
+  θ_merged = θ_base + Σ [ α_i * DARE(θ_i - θ_base, p) ],
+  where DARE(τ, p) denotes the operation of dropping parameters with probability p and rescaling the rest by 1/(1-p).   
   
 ### Models Merged