vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Add BPE pre-tokenization for DBRX.

Browse source
This commit is contained in:
DAN™ 2024-05-07 19:14:22 -04:00
parent b6aa670203
commit 18e447dd56
5 changed files with 10 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
convert-hf-to-gguf-update.py
View file

@ -68,6 +68,7 @@ models = [
{"name": "refact", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/smallcloudai/Refact-1_6-base", },
{"name": "command-r", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/CohereForAI/c4ai-command-r-v01", },
{"name": "olmo", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/allenai/OLMo-1.7-7B-hf", },
{"name": "dbrx", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/databricks/dbrx-base", },
]
# make directory "models/tokenizers" if it doesn't exist

3
convert-hf-to-gguf.py
View file

@ -317,6 +317,9 @@ class Model(ABC):
if chkhsh == "b6dc8df998e1cfbdc4eac8243701a65afe638679230920b50d6f17d81c098166":
# ref: https://huggingface.co/allenai/OLMo-1.7-7B-hf
res = "olmo"
if chkhsh == "a8594e3edff7c29c003940395316294b2c623e09894deebbc65f33f1515df79e":
# ref: https://huggingface.co/databricks/dbrx-instruct
res = "dbrx"
if res is None:
logger.warning("\n")

4
llama.cpp
View file

@ -4392,6 +4392,9 @@ static void llm_load_vocab(
} else if (
tokenizer_pre == "olmo") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_OLMO;
} else if (
tokenizer_pre == "dbrx") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DBRX;
} else {
throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
}
@ -12197,6 +12200,7 @@ struct llm_tokenizer_bpe {
case LLAMA_VOCAB_TYPE_BPE:
switch (vocab.type_pre) {
case LLAMA_VOCAB_PRE_TYPE_LLAMA3:
case LLAMA_VOCAB_PRE_TYPE_DBRX:
word_collection = unicode_regex_split(text, {
// original regex from tokenizer.json
//"(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",

1
llama.h
View file

@ -82,6 +82,7 @@ extern "C" {
LLAMA_VOCAB_PRE_TYPE_REFACT = 8,
LLAMA_VOCAB_PRE_TYPE_COMMAND_R = 9,
LLAMA_VOCAB_PRE_TYPE_OLMO = 10,
LLAMA_VOCAB_PRE_TYPE_DBRX = 11,
};
// note: these values should be synchronized with ggml_rope

1
tests/CMakeLists.txt
View file

@ -84,6 +84,7 @@ llama_test(test-tokenizer-0 NAME test-tokenizer-0-starcoder ARGS ${CMAKE
llama_test(test-tokenizer-0 NAME test-tokenizer-0-gpt-2 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-gpt-2.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-refact ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-refact.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-command-r ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-command-r.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-dbrx ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-dbrx.gguf)
# build test-tokenizer-1-bpe target once and add many tests
add_executable(test-tokenizer-1-bpe test-tokenizer-1-bpe.cpp)