vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

feat: example comments in embedding

Browse source
This commit is contained in:
Joan Martinez 2024-04-24 10:14:02 +02:00
parent dd060a2a4e
commit dfa067631c
1 changed files with 8 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

8
examples/embedding/embedding.cpp
View file

@ -49,6 +49,12 @@ static void batch_decode(llama_context * ctx, llama_batch & batch, float * outpu
} }
float * out = output + batch.seq_id[i][0] * n_embd; float * out = output + batch.seq_id[i][0] * n_embd;
//TODO: I would also add a parameter here to enable normalization or not.
/*fprintf(stdout, "unnormalized_embedding:");
for (int hh = 0; hh < n_embd; hh++) {
fprintf(stdout, "%9.6f ", embd[hh]);
}
fprintf(stdout, "\n");*/
llama_embd_normalize(embd, out, n_embd); llama_embd_normalize(embd, out, n_embd);
} }
} }
@ -124,6 +130,8 @@ int main(int argc, char ** argv) {
} }
// add SEP if not present // add SEP if not present
// JoanFM: I propose to remove this line so that user can make sure that their model is properly configured to tokenize as expected.
// We could also add a parameter, but I think that adding parameters specific for the examples can become messy and unmantaibable easy
for (auto & inp : inputs) { for (auto & inp : inputs) {
if (inp.empty() || inp.back() != llama_token_sep(model)) { if (inp.empty() || inp.back() != llama_token_sep(model)) {
inp.push_back(llama_token_sep(model)); inp.push_back(llama_token_sep(model));