mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 35 Packages Projects Releases Wiki Activity

convert : Mistral format yarn apply_scale support (#22612)

Browse Source 
* [BUGFIX] Mistral format apply_scale support.

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* fix misunderstood boolean parameters

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Julien Denize
2026-05-03 21:51:21 +02:00
committed by GitHub
parent db44417b02
commit 048a490f76
2 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+2 -2
View File
@@ -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;