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

BERT tokenizer fixes (#6498)

Browse source 
Key changes:
* BERT conversion: fix abuse of LlamaHfVocab, do not set BOS or EOS
* Nomic Embed conversion: pad vocab instead of slicing embedding tensor
* llama_tokenize: handle added special tokens like HF does
This commit is contained in:
Jared Van Bortel 2024-04-09 13:44:08 -04:00 • committed by GitHub
parent c4a3a4ff47
commit 1b67731e18
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
20 changed files with 221 additions and 194 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama.h
View file

@ -786,6 +786,8 @@ extern "C" {
// Special tokens
LLAMA_API llama_token llama_token_bos(const struct llama_model * model); // beginning-of-sentence
LLAMA_API llama_token llama_token_eos(const struct llama_model * model); // end-of-sentence
LLAMA_API llama_token llama_token_cls(const struct llama_model * model); // classification
LLAMA_API llama_token llama_token_sep(const struct llama_model * model); // sentence separator
LLAMA_API llama_token llama_token_nl (const struct llama_model * model); // next-line
// Returns -1 if unknown, 1 for true or 0 for false.
@ -808,16 +810,16 @@ extern "C" {
/// @param tokens The tokens pointer must be large enough to hold the resulting tokens.
/// @return Returns the number of tokens on success, no more than n_tokens_max
/// @return Returns a negative number on failure - the number of tokens that would have been returned
/// @param special Allow tokenizing special and/or control tokens which otherwise are not exposed and treated as plaintext.
/// Does not insert a leading space.
/// @param parse_special Allow tokenizing special and/or control tokens which otherwise are not exposed and treated
/// as plaintext. Does not insert a leading space.
LLAMA_API int32_t llama_tokenize(
const struct llama_model * model,
const char * text,
int32_t text_len,
llama_token * tokens,
int32_t n_tokens_max,
bool add_bos,
bool special);
bool add_special,
bool parse_special);
// Token Id -> Piece.
// Uses the vocabulary in the provided context.