tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 20:05:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

vocab : add ByteDance-Seed/Seed-Coder (#13423)

Browse Source
This commit is contained in:
Sigbjørn Skjæret
2025-05-10 22:08:07 +02:00
committed by GitHub
parent 15e6125a39
commit d2a4ef05c6
4 changed files with 16 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
convert_hf_to_gguf.py
View File

@ -798,6 +798,9 @@ class TextModel(ModelBase):
if chkhsh == "0e9433cbbb161f89e264eb32e8e64bfe69e834973ffca5d41d3948a604a3e2a3": if chkhsh == "0e9433cbbb161f89e264eb32e8e64bfe69e834973ffca5d41d3948a604a3e2a3":
# ref: https://huggingface.co/mistral-community/pixtral-12b # ref: https://huggingface.co/mistral-community/pixtral-12b
res = "pixtral" res = "pixtral"
if chkhsh == "d5f1dd6f980fec569fb218a81a7658ac45fc56b38c5a0adeb1c232fbe04ef5ec":
# ref: https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Base
res = "seed-coder"
if res is None: if res is None:
logger.warning("\n") logger.warning("\n")

1
convert_hf_to_gguf_update.py
View File

@ -116,6 +116,7 @@ models = [
{"name": "llama4", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct", }, {"name": "llama4", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct", },
{"name": "glm4", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/THUDM/glm-4-9b-hf", }, {"name": "glm4", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/THUDM/glm-4-9b-hf", },
{"name": "pixtral", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/mistral-community/pixtral-12b", }, {"name": "pixtral", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/mistral-community/pixtral-12b", },
{"name": "seed-coder", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Base", },
] ]

1
include/llama.h
View File

@ -112,6 +112,7 @@ extern "C" {
LLAMA_VOCAB_PRE_TYPE_BAILINGMOE = 32, LLAMA_VOCAB_PRE_TYPE_BAILINGMOE = 32,
LLAMA_VOCAB_PRE_TYPE_LLAMA4 = 33, LLAMA_VOCAB_PRE_TYPE_LLAMA4 = 33,
LLAMA_VOCAB_PRE_TYPE_PIXTRAL = 34, LLAMA_VOCAB_PRE_TYPE_PIXTRAL = 34,
LLAMA_VOCAB_PRE_TYPE_SEED_CODER = 35,
}; };
enum llama_rope_type { enum llama_rope_type {

11
src/llama-vocab.cpp
View File

@ -415,6 +415,13 @@ struct llm_tokenizer_bpe : llm_tokenizer {
"'(?:[sSdDmMtT]|[lL][lL]|[vV][eE]|[rR][eE])|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]|\\s+(?!\\S)|\\s+", "'(?:[sSdDmMtT]|[lL][lL]|[vV][eE]|[rR][eE])|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]|\\s+(?!\\S)|\\s+",
}; };
break; break;
case LLAMA_VOCAB_PRE_TYPE_SEED_CODER:
regex_exprs = {
// original regex from tokenizer.json
// "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1}| ?[^\\s\\p{L}\\p{N}\r\n]+|\\s*[\r\n]+|\\s+(?!\\S)|\\s+"
"(?:'[sS]|'[tT]|'[rR][eE]|'[vV][eE]|'[mM]|'[lL][lL]|'[dD])|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1}| ?[^\\s\\p{L}\\p{N}\\r\\n]+|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
};
break;
default: default:
// default regex for BPE tokenization pre-processing // default regex for BPE tokenization pre-processing
regex_exprs = { regex_exprs = {
@ -1634,6 +1641,10 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
tokenizer_pre == "bailingmoe") { tokenizer_pre == "bailingmoe") {
pre_type = LLAMA_VOCAB_PRE_TYPE_BAILINGMOE; pre_type = LLAMA_VOCAB_PRE_TYPE_BAILINGMOE;
clean_spaces = false; clean_spaces = false;
} else if (
tokenizer_pre == "seed-coder") {
pre_type = LLAMA_VOCAB_PRE_TYPE_SEED_CODER;
clean_spaces = false;
} else { } else {
throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str())); throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
} }