tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 12:25:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix comment for "output.weight" tensor

Browse Source
This commit is contained in:
Georgi Gerganov
2023-04-21 10:23:36 +03:00
parent 2510c1831f
commit d40fded93e
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
llama.cpp
View File

@ -1618,8 +1618,8 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
// quantize only 2D tensors
quantize &= (tensor.ne.size() == 2);
// GG: uncomment this to keep the output layer in FP16
//if (tensor.name.rfind("output")) {
// uncomment this to keep the output layer in FP16
//if (tensor.name == "output.weight") {
// quantize = false;
//}