public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-07 23:11:26 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source
This commit is contained in:
Georgi Gerganov
2026-03-16 13:10:15 +02:00
parent ab1252c19e
commit 2bc630f197
131 changed files with 2374 additions and 1519 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/talk-llama/models/jamba.cpp
+2 -2
View File
@@ -1,7 +1,7 @@
#include "models.h"
llm_build_jamba::llm_build_jamba(const llama_model & model, const llm_graph_params & params) : llm_build_mamba_base(params) {
const int64_t n_embd_head = hparams.n_embd_head_v;
const int64_t n_embd_head = hparams.n_embd_head_v();
ggml_tensor * cur;
ggml_tensor * inpL;
@@ -76,7 +76,7 @@ llm_build_jamba::llm_build_jamba(const llama_model & model, const llm_graph_para
nullptr,
n_expert, n_expert_used,
LLM_FFN_SILU, false,
false, 0.0,
hparams.expert_weights_scale,
LLAMA_EXPERT_GATING_FUNC_TYPE_SOFTMAX,
il);
cb(cur, "ffn_moe_out", il);