From f4ab2a41476600a98067a9474ea8f9e6db41bcfa Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Mon, 29 Apr 2024 16:58:41 +0300 Subject: llama : fix BPE pre-tokenization (#6920) * merged the changes from deepseeker models to main branch * Moved regex patterns to unicode.cpp and updated unicode.h * Moved header files * Resolved issues * added and refactored unicode_regex_split and related functions * Updated/merged the deepseek coder pr * Refactored code * Adding unicode regex mappings * Adding unicode regex function * Added needed functionality, testing remains * Fixed issues * Fixed issue with gpt2 regex custom preprocessor * unicode : fix? unicode_wstring_to_utf8 * lint : fix whitespaces * tests : add tokenizer tests for numbers * unicode : remove redundant headers * tests : remove and rename tokenizer test scripts * tests : add sample usage * gguf-py : reader prints warnings on duplicate keys * llama : towards llama3 tokenization support (wip) * unicode : shot in the dark to fix tests on Windows * unicode : first try custom implementations * convert : add "tokenizer.ggml.pre" GGUF KV (wip) * llama : use new pre-tokenizer type * convert : fix pre-tokenizer type writing * lint : fix * make : add test-tokenizer-0-llama-v3 * wip * models : add llama v3 vocab file * llama : adapt punctuation regex + add llama 3 regex * minor * unicode : set bomb * unicode : set bomb * unicode : always use std::wregex * unicode : support \p{N}, \p{L} and \p{P} natively * unicode : try fix windows * unicode : category support via std::regex * unicode : clean-up * unicode : simplify * convert : add convert-hf-to-gguf-update.py ggml-ci * lint : update * convert : add falcon ggml-ci * unicode : normalize signatures * lint : fix * lint : fix * convert : remove unused functions * convert : add comments * convert : exercise contractions ggml-ci * lint : fix * cmake : refactor test targets * tests : refactor vocab tests ggml-ci * tests : add more vocabs and tests ggml-ci * unicode : cleanup * scripts : ignore new update script in check-requirements.sh * models : add phi-3, mpt, gpt-2, starcoder * tests : disable obsolete ggml-ci * tests : use faster bpe test ggml-ci * llama : more prominent warning for old BPE models * tests : disable test-tokenizer-1-bpe due to slowness ggml-ci --------- Co-authored-by: Jaggzh Co-authored-by: Kazim Abrar Mahi --- llama.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'llama.h') diff --git a/llama.h b/llama.h index 8b1b15ed..30835de5 100644 --- a/llama.h +++ b/llama.h @@ -69,6 +69,18 @@ extern "C" { LLAMA_VOCAB_TYPE_WPM = 3, // BERT tokenizer based on WordPiece }; + // pre-tokenization types + enum llama_vocab_pre_type { + LLAMA_VOCAB_PRE_TYPE_DEFAULT = 0, + LLAMA_VOCAB_PRE_TYPE_LLAMA3 = 1, + LLAMA_VOCAB_PRE_TYPE_DEEPSEEK_LLM = 2, + LLAMA_VOCAB_PRE_TYPE_DEEPSEEK_CODER = 3, + LLAMA_VOCAB_PRE_TYPE_FALCON = 4, + LLAMA_VOCAB_PRE_TYPE_MPT = 5, + LLAMA_VOCAB_PRE_TYPE_STARCODER = 6, + LLAMA_VOCAB_PRE_TYPE_GPT2 = 7, + }; + // note: these values should be synchronized with ggml_rope // TODO: maybe move this enum to ggml.h (ggml_rope_type) enum llama_rope_type { -- cgit v1.2.3