vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-18 23:49:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

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
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 4 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

3
convert_hf_to_gguf.py
View file

@ -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:

4
src/llama-model.cpp
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;