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 --- common/common.cpp | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'common/common.cpp') diff --git a/common/common.cpp b/common/common.cpp index d42fa131..aa494291 100644 --- a/common/common.cpp +++ b/common/common.cpp @@ -1693,6 +1693,18 @@ std::vector string_split(std::string input, char separator) { return parts; } +std::string string_strip(const std::string & str) { + size_t start = 0; + size_t end = str.size(); + while (start < end && std::isspace(str[start])) { + start++; + } + while (end > start && std::isspace(str[end - 1])) { + end--; + } + return str.substr(start, end - start); +} + std::vector sampler_types_from_names(const std::vector & names, bool allow_alt_names) { std::unordered_map sampler_canonical_name_map { {"top_k", llama_sampler_type::TOP_K}, -- cgit v1.2.3