vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-09 19:46:11 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

model: add llama 4 scaling for mistral-large (deepseek arch) (#17744)

Browse source
This commit is contained in:
Xuan-Son Nguyen 2025-12-07 22:29:54 +01:00 • committed by GitHub
parent 08f9d3cc1d
commit 4d3726278b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 22 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

4
src/llama-model.cpp
View file

@ -1628,6 +1628,10 @@ void llama_model::load_hparams(llama_model_loader & ml) {
}
ml.get_key(LLM_KV_ROPE_SCALING_YARN_LOG_MUL, hparams.rope_yarn_log_mul, false);
// (optional) temperature tuning - used by mistral-large
ml.get_key(LLM_KV_ATTENTION_TEMPERATURE_SCALE, hparams.f_attn_temp_scale, false);
ml.get_key(LLM_KV_ATTENTION_TEMPERATURE_LENGTH, hparams.n_attn_temp_floor_scale, false);
switch (hparams.n_layer) {
case 27: type = LLM_TYPE_16B; break;
case 60: type = LLM_TYPE_236B; break;