Update llama.cpp

Author: abetlen

llama_cpp/llama_cpp.py

@@ -339,7 +339,7 @@ class llama_model_params(Structure):
 #     // ref: https://github.com/ggerganov/llama.cpp/pull/2054
 #     float    rope_freq_base;   // RoPE base frequency, 0 = from model
 #     float    rope_freq_scale;  // RoPE frequency scaling factor, 0 = from model
-#     float    yarn_ext_factor;  // YaRN extrapolation mix factor, NaN = from model
+#     float    yarn_ext_factor;  // YaRN extrapolation mix factor, negative = from model
 #     float    yarn_attn_factor; // YaRN magnitude scaling factor
 #     float    yarn_beta_fast;   // YaRN low correction dim
 #     float    yarn_beta_slow;   // YaRN high correction dim