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

llama : add option to render special/control tokens (#6807)

Browse source 
* make : fix common dep on llama.h

* llama : add option to render special tokens

* readme : add API change notice

ggml-ci

* swift : fix build
This commit is contained in:
Georgi Gerganov 2024-04-21 18:36:45 +03:00 • committed by GitHub
parent b9cc76d87e
commit 40f74e4d73
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 25 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama.h
View file

@ -828,11 +828,13 @@ extern "C" {
// Uses the vocabulary in the provided context.
// Does not write null terminator to the buffer.
// User code is responsible to remove the leading whitespace of the first non-BOS token when decoding multiple tokens.
// @param special If true, special tokens are rendered in the output.
LLAMA_API int32_t llama_token_to_piece(
const struct llama_model * model,
llama_token token,
char * buf,
int32_t length);
int32_t length,
bool special);
/// Apply chat template. Inspired by hf apply_chat_template() on python.
/// Both "model" and "custom_template" are optional, but at least one is required. "custom_template" has higher precedence than "model"