vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-13 10:29:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

model : support Qwen3-Embedding (#15023)

Browse source
This commit is contained in:
Douglas Hanley 2025-08-02 03:44:50 -05:00 • committed by GitHub
parent f906275537
commit 339bd0268c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 18 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

1
src/llama-model.cpp
View file

@ -899,6 +899,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
} break;
case LLM_ARCH_QWEN3:
{
ml.get_key(LLM_KV_POOLING_TYPE, hparams.pooling_type, false);
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
switch (hparams.n_layer) {
case 28: type = hparams.n_embd == 1024 ? LLM_TYPE_0_6B : LLM_TYPE_1_7B; break;