models : fix the attn_factor for mistral3 graphs + improve consistency (#17945)

* models : fix the attn_factor for mistral3 graphs

* cont : rework attn_factor correction logic

* cont : make deepseek2 consistent

* cont : add TODO

* cont : special-case DSv2

* cont : revert Mistral 3 Large changes

* cont : fix DS2 to use the original attn_factor

* cont : minor comments

src/llama-hparams.cpp

@@ -1,7 +1,9 @@
 #include "llama-hparams.h"
 
 #include "ggml.h"
+
 #include <cassert>
+#include <cmath>
 
 void llama_hparams::set_swa_pattern(uint32_t n_pattern, bool dense_first) {
     if (dense_first) {
@@ -229,3 +231,13 @@ bool llama_hparams::is_masked_swa(uint32_t n_swa, llama_swa_type swa_type, llama
 
     return false;
 }
+
+float llama_hparams::yarn_attn_factor_adjust(float attn_factor, float freq_scale, float ext_factor) {
+    GGML_ASSERT(ext_factor >= 0.0f);
+
+    if (ext_factor != 0.0f) {
+        attn_factor *= 1.0f / (1.0f + 0.1f * logf(1.0f / freq_scale));
+    }
+
+    return attn_factor;
+}