Update README.md

README.md

@@ -9,6 +9,6 @@ Following quantization suggestions in section 6.2 in the [Llama-3 paper](https:/
 - `token_embd` and `output` are in F16 precision;
 - The attention layers are in F16 precision;
 - The entirety of the first and final transformer layers are in F16 precision;
-- The feed-forward network (FFN) layers are in low precision.
+- The feed-forward network (FFN) layers are in **low** precision.
 
 For the same total model size, perplexity values might not be favorable compared to more uniformly quantized models, but supposedly this quantization scheme might help with real-world long-context performance and complex tasks. Your mileage may vary.