CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

embedding: assign n_ubatch value, print error on n_batch overflow

Browse Source
This commit is contained in:
Minsoo Cheong
2024-03-25 20:22:02 +09:00
parent ad3a0505e3
commit 6e27406352
1 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/embedding/embedding.cpp
View File

@@ -61,6 +61,8 @@ int main(int argc, char ** argv) {
}
params.embedding = true;
// For BERT models, batch size must be equal to ubatch size
params.n_ubatch = params.n_batch;
print_build_info();
@@ -114,7 +116,9 @@ 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);
}