root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-14 04:24:30 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

fix breaking change

Browse Source
This commit is contained in:
Ebey Abraham 2023-12-16 00:41:06 +00:00
parent 12cc80cb89
commit e20765534d
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
llama.cpp
View File

@ -5591,7 +5591,7 @@ struct llm_build_context {
cb(cur, "result_norm", -1);
cur = ggml_mul_mat(ctx0, model.output, cur);
cb(cur, "result_output", -1);
cb(cur, "result_norm", -1);
cur = ggml_add(ctx0, cur, model.output_b);
cb(cur, "result_output", -1);
@ -6236,7 +6236,7 @@ static int llama_decode_internal(
ggml_allocr_alloc_graph(lctx.alloc, gf);
struct ggml_tensor * res = gf->nodes[gf->n_nodes - 1];
struct ggml_tensor * embeddings = gf->nodes[gf->n_nodes - 3];
struct ggml_tensor * embeddings = gf->nodes[gf->n_nodes - 2];
GGML_ASSERT(strcmp(res->name, "result_output") == 0);
GGML_ASSERT(strcmp(embeddings->name, "result_norm") == 0);