root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-09-22 21:16:20 +00:00
Code Issues Actions 16 Packages Projects Releases Wiki Activity

llama : add Smaug 70B support (#7402)

Browse Source
This commit is contained in:
Bartowski 2024-05-26 08:28:35 -04:00 committed by GitHub
parent 9146d36fe7
commit c429b33beb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -81,6 +81,7 @@ models = [
{"name": "jina-v2-en", "tokt": TOKENIZER_TYPE.WPM, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-en", }, # WPM!
{"name": "jina-v2-es", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-es", },
{"name": "jina-v2-de", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-de", },
{"name": "smaug-bpe", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/abacusai/Smaug-Llama-3-70B-Instruct", },
]

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

@ -473,6 +473,9 @@ class Model:
if chkhsh == "27949a2493fc4a9f53f5b9b029c82689cfbe5d3a1929bb25e043089e28466de6":
# ref: https://huggingface.co/jinaai/jina-embeddings-v2-base-de
res = "jina-v2-de"
if chkhsh == "c136ed14d01c2745d4f60a9596ae66800e2b61fa45643e72436041855ad4089d":
# ref: https://huggingface.co/abacusai/Smaug-Llama-3-70B-Instruct
res = "smaug-bpe"
if res is None:
logger.warning("\n")

4
llama.cpp
View File

@ -4593,6 +4593,9 @@ static void llm_load_vocab(
} else if (
tokenizer_pre == "dbrx") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DBRX;
} else if (
tokenizer_pre == "smaug-bpe") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_SMAUG;
} else {
throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
}
@ -12512,6 +12515,7 @@ struct llm_tokenizer_bpe {
});
break;
case LLAMA_VOCAB_PRE_TYPE_DBRX:
case LLAMA_VOCAB_PRE_TYPE_SMAUG:
word_collection = unicode_regex_split(text, {
// same as llama3
"(?:'[sS]|'[tT]|'[rR][eE]|'[vV][eE]|'[mM]|'[lL][lL]|'[dD])|[^\\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

@ -85,6 +85,7 @@ extern "C" {
LLAMA_VOCAB_PRE_TYPE_QWEN2 = 11,
LLAMA_VOCAB_PRE_TYPE_OLMO = 12,
LLAMA_VOCAB_PRE_TYPE_DBRX = 13,
LLAMA_VOCAB_PRE_TYPE_SMAUG = 14,
};
// note: these values should be synchronized with ggml_rope