CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

command-r : add BPE pre-tokenization (#7063)

Browse Source 
* Add BPE pre-tokenization for Command-R/R+.

* Bump transformers convert requirement.

* command-r : add individual digits regex

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
DAN™
2024-05-05 01:19:30 -04:00
committed by GitHub
parent 6fbd432211
commit 889bdd7686
9 changed files with 168 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
llama.cpp
View File

@@ -4386,6 +4386,9 @@ static void llm_load_vocab(
} else if (
tokenizer_pre == "refact") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_REFACT;
} else if (
tokenizer_pre == "command-r") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_COMMAND_R;
} else {
throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
}
@@ -12238,6 +12241,7 @@ struct llm_tokenizer_bpe {
break;
case LLAMA_VOCAB_PRE_TYPE_STARCODER:
case LLAMA_VOCAB_PRE_TYPE_REFACT:
case LLAMA_VOCAB_PRE_TYPE_COMMAND_R:
word_collection = unicode_regex_split(text, {
"\\p{N}",
"'s|'t|'re|'ve|'m|'ll|'d| ?\\p{L}+| ?\\p{N}+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)",