jdelony/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-06-28 04:30:15 -05:00
Code Issues Packages Projects Releases Wiki Activity

Check for output_extra.weight when loading Gemma4 assistant models

Browse Source
This commit is contained in:
Kawrakow 2026-05-17 14:24:04 +00:00
parent 0ab9bdf793
commit 544fc08db2
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/llama-load-tensors.cpp
View File

@ -2150,6 +2150,10 @@ bool create_tensors_helper::create_gemma4_mtp_tensors(const LLM_TN & tn) {
model.tok_embd = create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);
model.output_norm = create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
model.output = create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, llama_model_loader::TENSOR_NOT_REQUIRED);
auto output_extra = create_tensor(ctx_output, "output_extra.weight", {n_embd, n_vocab}, llama_model_loader::TENSOR_NOT_REQUIRED);
if (output_extra) {
model.output = output_extra;
}
if (model.output == NULL) {
model.output = create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, llama_model_loader::TENSOR_DUPLICATED);
}