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 commit '32c8486e1f' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/nix/package.nix
#	CMakeLists.txt
#	Makefile
#	Package.swift
#	README.md
#	build.zig
#	llama.cpp
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2024-04-07 20:39:17 +08:00
commit 22f543d09b
32 changed files with 3521 additions and 1792 deletions
Download patch file Download diff file Expand all files Collapse all files

6
examples/embedding/embedding.cpp
View file

@ -62,6 +62,8 @@ int main(int argc, char ** argv) {
}
params.embedding = true;
// For non-causal models, batch size must be equal to ubatch size
params.n_ubatch = params.n_batch;
print_build_info();
@ -115,7 +117,9 @@ int main(int argc, char ** argv) {
for (const auto & prompt : prompts) {
auto inp = ::llama_tokenize(ctx, prompt, true, false);
if (inp.size() > n_batch) {
inp.resize(n_batch);
fprintf(stderr, "%s: error: number of tokens in input line (%lld) exceeds batch size (%lld), increase batch size and re-run\n",
__func__, (long long int) inp.size(), (long long int) n_batch);
return 1;
}
inputs.push_back(inp);
}