llama : Add support for DeepSeek V3 (#11049)

* convert : extend DEEPSEEK2 model architecture to support DeepseekV3ForCausalLM by adding EXPERT_WEIGHTS_NORM and EXPERT_GATING_FUNC model parameters and FFN_EXP_PROBS_B tensor type

* vocab : add DeepSeek V3 pre-tokenizer regexes

* unicode : handle ACCENT_MARK and SYMBOL categories in regex

* llama : add DeepSeek V3 chat template, handle new model parameters and tensor types

---------

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
This commit is contained in:
fairydreaming 2025-01-04 21:06:11 +01:00 committed by GitHub
parent f922a9c542
commit 9394bbd484
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
16 changed files with 162 additions and 5 deletions

View file

@ -667,18 +667,24 @@ std::vector<std::string> unicode_regex_split(const std::string & text, const std
{ "\\p{N}", unicode_cpt_flags::NUMBER },
{ "\\p{L}", unicode_cpt_flags::LETTER },
{ "\\p{P}", unicode_cpt_flags::PUNCTUATION },
{ "\\p{M}", unicode_cpt_flags::ACCENT_MARK },
{ "\\p{S}", unicode_cpt_flags::SYMBOL },
};
static const std::map<int, int> k_ucat_cpt = {
{ unicode_cpt_flags::NUMBER, 0xD1 },
{ unicode_cpt_flags::LETTER, 0xD2 },
{ unicode_cpt_flags::PUNCTUATION, 0xD3 },
{ unicode_cpt_flags::ACCENT_MARK, 0xD4 },
{ unicode_cpt_flags::SYMBOL, 0xD5 },
};
static const std::map<int, std::string> k_ucat_map = {
{ unicode_cpt_flags::NUMBER, "\x30-\x39" }, // 0-9
{ unicode_cpt_flags::LETTER, "\x41-\x5A\x61-\x7A" }, // A-Za-z
{ unicode_cpt_flags::PUNCTUATION, "\x21-\x23\x25-\x2A\x2C-\x2F\x3A-\x3B\x3F-\x40\\\x5B-\\\x5D\x5F\\\x7B\\\x7D" }, // !-#%-*,-/:-;?-@\[-\]_\{\}
{ unicode_cpt_flags::ACCENT_MARK, "" }, // no sub-128 codepoints
{ unicode_cpt_flags::SYMBOL, "\\\x24\\\x2B\x3C-\x3E\x5E\x60\\\x7C" }, // $+<=>^`|
};
// compute collapsed codepoints only if needed by at least one regex