convert : Mistral format yarn apply_scale support (#22612)

* [BUGFIX] Mistral format apply_scale support.

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <redacted>
* fix misunderstood boolean parameters

---------

Co-authored-by: Sigbjørn Skjæret <redacted>

diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py
index af3c4bad7e0486da4586b8aba3ebba38d15347db..7f4a4018f4f20676f5a4f01f16cd32b00f3eb151 100755 (executable)
--- a/convert_hf_to_gguf.py
+++ b/convert_hf_to_gguf.py
@@ -12716,11 +12716,12 @@ class MistralModel(LlamaModel):
     def set_mistral_config(gguf_writer: gguf.GGUFWriter, hparams: dict):
         if "yarn" in hparams:
             yarn_params = hparams["yarn"]
+            mscale_all_dim = 1.0 if not yarn_params["apply_scale"] else 0.0
             gguf_writer.add_rope_scaling_type(gguf.RopeScalingType.YARN)
             gguf_writer.add_rope_scaling_factor(yarn_params["factor"])
             gguf_writer.add_rope_scaling_yarn_beta_fast(yarn_params["beta"])
             gguf_writer.add_rope_scaling_yarn_beta_slow(yarn_params["alpha"])
-            gguf_writer.add_rope_scaling_yarn_log_mul(1.0) # mscale_all_dim
+            gguf_writer.add_rope_scaling_yarn_log_mul(mscale_all_dim)
             gguf_writer.add_rope_scaling_orig_ctx_len(yarn_params["original_max_position_embeddings"])
 
         if "llama_4_scaling" in hparams:

diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index 9e2a13cbd43ef203f1381cc364877490db0aeb89..54caff987d1483dbe5ad5a45e24a600b13aa3116 100644 (file)
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -1994,7 +1994,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
                     }
                 }
 
-                if (ml.get_key(LLM_KV_ROPE_SCALING_YARN_LOG_MUL, hparams.rope_yarn_log_mul, 0.0f)) {
+                if (ml.get_key(LLM_KV_ROPE_SCALING_YARN_LOG_MUL, hparams.rope_yarn_log_mul, false)) {
                     // [TAG_DEEPSEEK2_YARN_LOG_MUL_FIX]
                     // cancel the factor from the convert script
                     hparams.rope_yarn_log_mul /= 0.1f;
@@ -2868,7 +2868,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
 
                 ml.get_key(LLM_KV_ROPE_SCALING_YARN_BETA_FAST, hparams.yarn_beta_fast,    false);
                 ml.get_key(LLM_KV_ROPE_SCALING_YARN_BETA_SLOW, hparams.yarn_beta_slow,    false);
-                ml.get_key(LLM_KV_ROPE_SCALING_YARN_LOG_MUL,   hparams.rope_yarn_log_mul, 0.0f);
+                ml.get_key(LLM_KV_ROPE_SCALING_YARN_LOG_MUL,   hparams.rope_yarn_log_mul, false);
 
                 hparams.f_attn_temp_offset = 0.0f;