llama : support more diverse tokenizers? (#2420)

* supporting more diverse tokenizers

* Update llama.cpp

---------

Co-authored-by: Georgi Gerganov <redacted>

diff --git a/llama.cpp b/llama.cpp
index a4489773f96c5b2f24697df372c6fbd05a1c8f79..a35c690ea9f68ccbe97c0b78652300fe6653c335 100644 (file)
--- a/llama.cpp
+++ b/llama.cpp
@@ -1924,7 +1924,9 @@ struct llama_tokenizer {
             if (token == vocab_.token_to_id.end()) {
                 // output any symbols that did not form tokens as bytes.
                 for (int j = 0; j < (int) symbol.n; ++j) {
-                    llama_vocab::id token_id = static_cast<uint8_t>(symbol.text[j]) + 3;
+                    // NOTE: old version, before #2420 - not sure what are the implications of this
+                    //llama_vocab::id token_id = static_cast<uint8_t>(symbol.text[j]) + 3;
+                    llama_vocab::id token_id = vocab_.token_to_id.at(std::string(1, symbol.text[j]));
                     output.push_back(token_id);
                 }
             } else {