ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-25 15:44:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Forgotten counter increment

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-02-05 08:14:26 +02:00
parent 19d384302b
commit 0467c16a7f
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/llama.cpp
View File

@@ -16098,6 +16098,7 @@ static ggml_type llama_tensor_get_type(quantize_state_internal & qs, ggml_type n
else if (i_layer < n_layer/8) {
new_type = GGML_TYPE_Q2_K_R4;
}
++qs.i_ffn_down;
}
else if (name.find("attn_output.weight") != std::string::npos) {
new_type = qs.model.hparams.n_expert >= 4 ? GGML_TYPE_Q5_K_R4 : GGML_TYPE_IQ2_K_R4;