vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into concedo_experimental

Browse source 
# Conflicts:
#	.flake8
#	.github/workflows/python-lint.yml
#	flake.lock
#	ggml-cuda.cu
#	ggml-quants.c
#	llama.cpp
#	pocs/vdot/q8dot.cpp
#	pocs/vdot/vdot.cpp
#	tests/test-quantize-fns.cpp
#	tests/test-quantize-perf.cpp
This commit is contained in:
Concedo 2024-02-13 00:14:22 +08:00
commit 3cec37c2e0
35 changed files with 2814 additions and 1749 deletions
Download patch file Download diff file Expand all files Collapse all files

12
examples/embedding/embedding.cpp
View file

@ -88,7 +88,17 @@ int main(int argc, char ** argv) {
}
const int n_embd = llama_n_embd(model);
const auto * embeddings = llama_get_embeddings(ctx);
auto * embeddings = llama_get_embeddings(ctx);
// l2-normalize embeddings
float norm = 0;
for (int i = 0; i < n_embd; i++) {
norm += embeddings[i] * embeddings[i];
}
norm = sqrt(norm);
for (int i = 0; i < n_embd; i++) {
embeddings[i] /= norm;
}
for (int i = 0; i < n_embd; i++) {
printf("%f ", embeddings[i]);