EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

model : add Granite Hybrid nano types (#16896)

Browse Source 
Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>
This commit is contained in:
Giuseppe Scrivano
2025-10-31 21:20:07 +01:00
committed by GitHub
parent 31c511a968
commit e58d585604
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/llama-model.cpp
View File

@@ -1898,7 +1898,8 @@ void llama_model::load_hparams(llama_model_loader & ml) {
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
switch (hparams.n_embd) {
case 1536: type = LLM_TYPE_7B_A1B; break;
case 768: type = LLM_TYPE_350M; break;
case 1536: type = (hparams.n_embd == 2048 ? LLM_TYPE_7B_A1B : LLM_TYPE_1B); break;
case 2048: case 2560: type = LLM_TYPE_3B; break;
case 4096: type = LLM_TYPE_32B; break;
default: type = LLM_TYPE_UNKNOWN;