tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-01 13:05:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : add DRY sampler (#9702)

Browse Source 
* sampling : add DRY sampler (post-refactor)

* DRY: Trying to fix coauthors, removed unneeded line

* DRY: Fixed redundant code

* DRY: Fixed crash issue due to DRY being in chain but uninitialized

---------

Co-authored-by: l3utterfly <gc.pthzfoldr@gmail.com>
Co-authored-by: pi6am <34464159+pi6am@users.noreply.github.com>
This commit is contained in:
wwoodsTM
2024-10-25 10:07:34 -06:00
committed by GitHub
parent d80fb71f8b
commit ff252ea48e
17 changed files with 713 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
src/llama-vocab.cpp
View File

@ -1966,3 +1966,19 @@ int32_t llama_detokenize_impl(
return total <= text_len_max ? total : -total;
}
std::string llama_detokenize(const struct llama_vocab & vocab, const std::vector<llama_token> & tokens, bool special) {
std::string text;
text.resize(std::max(text.capacity(), tokens.size()));
int32_t n_chars = llama_detokenize_impl(vocab, tokens.data(), (int32_t)tokens.size(), &text[0], (int32_t)text.size(), false, special);
if (n_chars < 0) {
text.resize(-n_chars);
n_chars = llama_detokenize_impl(vocab, tokens.data(), (int32_t)tokens.size(), &text[0], (int32_t)text.size(), false, special);
GGML_ASSERT(n_chars <= (int32_t)text.size()); // whitespace trimming is performed after per-token detokenization
}
text.resize(n_chars);
// NOTE: the original tokenizer decodes bytes after collecting the pieces.
return text;
}