Skip to content

convert : fix nomic-bert-moe mask token #13757

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 9 commits into from
Jun 1, 2025
Merged

convert : fix nomic-bert-moe mask token #13757

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
cb5d91b
add missing mask token
CISC May 24, 2025
c55c1ba
set mask token lstrip attribute
CISC May 24, 2025
57c8470
str -> bytes
CISC May 24, 2025
5030d48
Merge branch 'master' into cisc/fix-nomic-bert-moe-mask
CISC May 29, 2025
958eea6
remove dead padding code that got readded in merge
CISC May 29, 2025
7789616
apply correct padding with AutoTokenizer as well
CISC Jun 1, 2025
a835a0c
spaces--
CISC Jun 1, 2025
2946277
Merge branch 'master' into cisc/fix-nomic-bert-moe-mask
CISC Jun 1, 2025
4f2f228
only add mask token when using sentencepiece
CISC Jun 1, 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
6 changes: 6 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 @@ -3889,6 +3889,12 @@ def _xlmroberta_set_vocab(self) -> None:
SentencePieceTokenTypes.UNKNOWN,
] + toktypes[3:-1]

if self.model_arch == gguf.MODEL_ARCH.NOMIC_BERT_MOE:
# Add mask token missing from sentencepiece.bpe.model
tokens[250001] = b'<mask>'
scores[250001] = 0.0
toktypes[250001] = SentencePieceTokenTypes.CONTROL

self.gguf_writer.add_tokenizer_model("t5")
self.gguf_writer.add_tokenizer_pre("default")
self.gguf_writer.add_token_list(tokens)
Expand Down
9 changes: 7 additions & 2 deletions src/llama-vocab.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2080,9 +2080,11 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {

std::string model_name;
std::string tokenizer_pre;
std::string general_arch;

ml.get_key(LLM_KV_GENERAL_NAME, model_name, false);
ml.get_key(LLM_KV_TOKENIZER_PRE, tokenizer_pre, false);
ml.get_key(LLM_KV_GENERAL_ARCHITECTURE, general_arch, false);

// model name to lowercase
std::transform(model_name.begin(), model_name.end(), model_name.begin(),
Expand All @@ -2091,8 +2093,11 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
}
);

// set attributes by model/tokenizer name
if (_contains_any(tokenizer_pre, {"jina-v2-de", "jina-v2-es", "jina-v2-code"})) {
// set attributes by model/tokenizer/architecture name
if (false
|| _contains_any(tokenizer_pre, {"jina-v2-de", "jina-v2-es", "jina-v2-code"})
|| _contains_any(general_arch, {"nomic-bert-moe"})
) {
_set_token_attr("<mask>", LLAMA_TOKEN_ATTR_LSTRIP, true);
} else if (_contains_any(model_name, {"phi-3", "phi3"})) {
for (auto id : cache_special_tokens) {
Expand Down
Loading