Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-12 05:17:21 +01:00
Code Issues Packages Projects Releases Wiki Activity

embedding : adjust n_ubatch value (#6296)

Browse Source 
* embedding: assign `n_ubatch` value, print error on `n_batch` overflow

* Update examples/embedding/embedding.cpp

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>

* use %ld instead of %lld

* Revert "use %ld instead of %lld"

This reverts commit ea753ede90a86a0699f65878cc8e2020ff5eabb8.

---------

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
This commit is contained in:
Minsoo Cheong 2024-03-26 18:11:46 +09:00 committed by GitHub
parent 3d032ece8e
commit deb7240100
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 1 deletions
Show Stats 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; params.embedding = true;
// For non-causal models, batch size must be equal to ubatch size
params.n_ubatch = params.n_batch;
print_build_info(); print_build_info();
@ -114,7 +116,9 @@ int main(int argc, char ** argv) {
for (const auto & prompt : prompts) { for (const auto & prompt : prompts) {
auto inp = ::llama_tokenize(ctx, prompt, true, false); auto inp = ::llama_tokenize(ctx, prompt, true, false);
if (inp.size() > n_batch) { 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); inputs.push_back(inp);
} }