public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-18 21:55:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source
This commit is contained in:
Georgi Gerganov
2026-06-15 10:33:53 +03:00
parent 0a3fa9ca17
commit 0ec0845110
25 changed files with 671 additions and 96 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/talk-llama/models/gemma4-assistant.cpp
+3
View File
@@ -39,6 +39,9 @@ void llama_model_gemma4_assistant::load_arch_tensors(llama_model_loader &) {
output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), { n_embd }, 0);
create_tensor(tn(LLM_TENSOR_MASKED_EMBD_CENTROIDS, "weight"), {}, TENSOR_NOT_REQUIRED);
create_tensor(tn(LLM_TENSOR_MASKED_EMBD_ORDERING), {}, TENSOR_NOT_REQUIRED);
const int64_t n_embd_backbone = hparams.n_embd_inp();
nextn_proj_post = create_tensor(tn(LLM_TENSOR_NEXTN_PROJ_POST, "weight"), { n_embd, n_embd_backbone }, 0);