diff options
Diffstat (limited to 'examples')
| -rw-r--r-- | examples/embedding/embedding.cpp | 12 |
1 files changed, 10 insertions, 2 deletions
diff --git a/examples/embedding/embedding.cpp b/examples/embedding/embedding.cpp index 6a93147d..c85a2da5 100644 --- a/examples/embedding/embedding.cpp +++ b/examples/embedding/embedding.cpp @@ -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; + //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); } } @@ -123,10 +129,12 @@ int main(int argc, char ** argv) { inputs.push_back(inp); } - // add SEP if not present + // check if the last token is SEP + // it should be automatically added by the tokenizer when 'tokenizer.ggml.add_eos_token' is set to 'true' for (auto & inp : inputs) { if (inp.empty() || inp.back() != llama_token_sep(model)) { - inp.push_back(llama_token_sep(model)); + fprintf(stderr, "%s: warning: last token in the prompt is not SEP\n", __func__); + fprintf(stderr, "%s: 'tokenizer.ggml.add_eos_token' should be set to 'true' in the GGUF header\n", __func__); } } |