thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

model : add KORMo model (#18032)

Browse source 
* vocab: add KORMo Tokenizer

* model: add KORMoForCausalLM

* vocab: change pretokenizer to qwen2

* lint: fix unintended line removal

* model: make qwen2 bias tensor optional

* model: use qwen2 architecture for KORMo
This commit is contained in:
HelloKS 2025-12-16 02:51:43 +09:00 • committed by GitHub
parent 4529c660c8
commit 9d52f17ae3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 25 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

15
src/models/qwen2.cpp
View file

@ -31,16 +31,25 @@ llm_build_qwen2::llm_build_qwen2(const llama_model & model, const llm_graph_para
{
// compute Q and K and RoPE them
ggml_tensor * Qcur = build_lora_mm(model.layers[il].wq, cur);
Qcur = ggml_add(ctx0, Qcur, model.layers[il].bq);
cb(Qcur, "Qcur", il);
if (model.layers[il].bq) {
Qcur = ggml_add(ctx0, Qcur, model.layers[il].bq);
cb(Qcur, "Qcur", il);
}
ggml_tensor * Kcur = build_lora_mm(model.layers[il].wk, cur);
Kcur = ggml_add(ctx0, Kcur, model.layers[il].bk);
cb(Kcur, "Kcur", il);
if (model.layers[il].bk) {
Kcur = ggml_add(ctx0, Kcur, model.layers[il].bk);
cb(Kcur, "Kcur", il);
}
ggml_tensor * Vcur = build_lora_mm(model.layers[il].wv, cur);
Vcur = ggml_add(ctx0, Vcur, model.layers[il].bv);
cb(Vcur, "Vcur", il);
if (model.layers[il].bv) {
Vcur = ggml_add(ctx0, Vcur, model.layers[il].bv);
cb(Vcur, "Vcur", il);
}
Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens);
Kcur = ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens);