Skip to content

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

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
May 10, 2025
Merged

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

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
2c7c0f5
add seed-coder vocab
CISC May 10, 2025
bf33e5a
add seed-coder vocab
CISC May 10, 2025
5732ffe
add seed-coder vocab
CISC May 10, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions convert_hf_to_gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -794,6 +794,9 @@ def get_vocab_base_pre(self, tokenizer) -> str:
if chkhsh == "0e9433cbbb161f89e264eb32e8e64bfe69e834973ffca5d41d3948a604a3e2a3":
# ref: https://huggingface.co/mistral-community/pixtral-12b
res = "pixtral"
if chkhsh == "d5f1dd6f980fec569fb218a81a7658ac45fc56b38c5a0adeb1c232fbe04ef5ec":
# ref: https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Base
res = "seed-coder"

if res is None:
logger.warning("\n")
Expand Down
1 change: 1 addition & 0 deletions convert_hf_to_gguf_update.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,6 +116,7 @@ class TOKENIZER_TYPE(IntEnum):
{"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": "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", },
]


Expand Down
1 change: 1 addition & 0 deletions include/llama.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,6 +112,7 @@ extern "C" {
LLAMA_VOCAB_PRE_TYPE_BAILINGMOE = 32,
LLAMA_VOCAB_PRE_TYPE_LLAMA4 = 33,
LLAMA_VOCAB_PRE_TYPE_PIXTRAL = 34,
LLAMA_VOCAB_PRE_TYPE_SEED_CODER = 35,
};

enum llama_rope_type {
Expand Down
11 changes: 11 additions & 0 deletions src/llama-vocab.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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+",
};
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 regex for BPE tokenization pre-processing
regex_exprs = {
Expand Down Expand Up @@ -1634,6 +1641,10 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
tokenizer_pre == "bailingmoe") {
pre_type = LLAMA_VOCAB_PRE_TYPE_BAILINGMOE;
clean_spaces = false;
} else if (
tokenizer_pre == "seed-coder") {
pre_type = LLAMA_VOCAB_PRE_TYPE_SEED_CODER;
clean_spaces = false;
} else {
throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
}
Expand Down
Loading