ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-08 23:40:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Allow distinct output tensor for Gemma models (#969)

Browse Source 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-11-16 12:12:41 +02:00
committed by GitHub
parent 03da76eb05
commit 4d003e29ee
2 changed files with 7 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/llama-model.cpp
View File

@@ -639,6 +639,7 @@ static const std::map<llm_arch, std::map<llm_tensor, std::string>> LLM_TENSOR_NA
{
{ LLM_TENSOR_TOKEN_EMBD, "token_embd" },
{ LLM_TENSOR_OUTPUT_NORM, "output_norm" },
{ LLM_TENSOR_OUTPUT, "output" },
{ LLM_TENSOR_ATTN_NORM, "blk.%d.attn_norm" },
{ LLM_TENSOR_ATTN_Q, "blk.%d.attn_q" },
{ LLM_TENSOR_ATTN_Q_NORM, "blk.%d.attn_q_norm" },