diff --git a/README.md b/README.md
index 198f39c..bfc7377 100644
--- a/README.md
+++ b/README.md
@@ -24,7 +24,7 @@ tags:
 
 ## <span style="color: #7F7FFF;">Model Generation Details</span>
 
-This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`f505bd83`](https://github.com/ggerganov/llama.cpp/commit/f505bd83ca7a43c4585ff3d59135e77eae9c793b).
+This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`ee09828cb`](https://github.com/ggerganov/llama.cpp/commit/ee09828cb057460b369576410601a3a09279e23c).
 
 
 
@@ -131,6 +131,8 @@ However, we do not recommend using them for tasks that are knowledge-intensive o
 * `min_p=0.15`
 * `repetition_penalty=1.05`
 
+**Reasoning**: LFM2-2.6B is the only model in this family to use dynamic hybrid reasoning (traces between `<think>` and `</think>` tokens) for complex or multilingual prompts.
+
 **Chat template**: LFM2 uses a ChatML-like chat template as follows:
 
 ```