upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-07 02:20:48 -05:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into HEAD

Browse Source
This commit is contained in:
Georgi Gerganov
2025-12-08 17:55:24 +02:00
parent 72e3681073 68522c678d
commit 6d38db5dfe
48 changed files with 20773 additions and 528 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;