From edd4c1481708fcd788b0e423268304fd26e2b125 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Sun, 27 Aug 2023 14:19:19 +0300 Subject: llama : more tokenizer fixes (#2810) * tests : write a Python tokenizer test (wip) * llama : prefix input text for tokenization with whitespace * llama : distinguish pieces from decoded text + fix detokenization * common : add comments * examples : no longer manually add leading space when tokenizing * tests : use Python to generate tokenizer tests for C++ * tests : add option to tokenize text files ggml-ci * tests : add test-tokenizer-1.py * llama.cpp : fix LF token * hellaswag : move the concat space for clarity * tests : add falcon tests (py + cpp, currently do not pass Unicode) ggml-ci * common : temporary separate llama_detokenize calls for SPM and BPE --------- Co-authored-by: klosax <131523366+klosax@users.noreply.github.com> --- examples/embedding/embedding.cpp | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'examples/embedding/embedding.cpp') diff --git a/examples/embedding/embedding.cpp b/examples/embedding/embedding.cpp index 38395c75..93d583b5 100644 --- a/examples/embedding/embedding.cpp +++ b/examples/embedding/embedding.cpp @@ -56,9 +56,6 @@ int main(int argc, char ** argv) { int n_past = 0; - // Add a space in front of the first character to match OG llama tokenizer behavior - params.prompt.insert(0, 1, ' '); - // tokenize the prompt auto embd_inp = ::llama_tokenize(ctx, params.prompt, true); @@ -67,7 +64,7 @@ int main(int argc, char ** argv) { fprintf(stderr, "%s: prompt: '%s'\n", __func__, params.prompt.c_str()); fprintf(stderr, "%s: number of tokens in prompt = %zu\n", __func__, embd_inp.size()); for (int i = 0; i < (int) embd_inp.size(); i++) { - fprintf(stderr, "%6d -> '%s'\n", embd_inp[i], llama_token_to_str(ctx, embd_inp[i]).c_str()); + fprintf(stderr, "%6d -> '%s'\n", embd_inp[i], llama_token_to_piece(ctx, embd_inp[i]).c_str()); } fprintf(stderr, "\n"); } -- cgit v1.2.3