Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 13:28:50 +01:00
Code Issues Packages Projects Releases Wiki Activity

embedding : add EOS token if not present (#899)

Browse Source
This commit is contained in:
Georgi Gerganov 2024-03-14 15:14:14 +02:00
parent 77178eedc8
commit 044ec4b2a5
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 9 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
examples/embedding/embedding.cpp
View File

@ -112,13 +112,20 @@ int main(int argc, char ** argv) {
// tokenize the prompts and trim // tokenize the prompts and trim
std::vector<std::vector<int32_t>> inputs; std::vector<std::vector<int32_t>> inputs;
for (const auto & prompt : prompts) { for (const auto & prompt : prompts) {
auto inp = ::llama_tokenize(ctx, prompt, true); auto inp = ::llama_tokenize(ctx, prompt, true, false);
if (inp.size() > n_batch) { if (inp.size() > n_batch) {
inp.resize(n_batch); inp.resize(n_batch);
} }
inputs.push_back(inp); inputs.push_back(inp);
} }
// add eos if not present
for (auto & inp : inputs) {
if (inp.empty() || inp.back() != llama_token_eos(model)) {
inp.push_back(llama_token_eos(model));
}
}
// tokenization stats // tokenization stats
if (params.verbose_prompt) { if (params.verbose_prompt) {
for (int i = 0; i < (int) inputs.size(); i++) { for (int i = 0; i < (int) inputs.size(); i++) {
@ -172,7 +179,7 @@ int main(int argc, char ** argv) {
for (int j = 0; j < n_prompts; j++) { for (int j = 0; j < n_prompts; j++) {
fprintf(stdout, "embedding %d: ", j); fprintf(stdout, "embedding %d: ", j);
for (int i = 0; i < std::min(16, n_embd); i++) { for (int i = 0; i < std::min(16, n_embd); i++) {
fprintf(stdout, "%f ", emb[j * n_embd + i]); fprintf(stdout, "%9.6f ", emb[j * n_embd + i]);
} }
fprintf(stdout, "\n"); fprintf(stdout, "\n");
} }