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

common : revert showing control tokens by default for server (#6860)

Browse source 
* fix: revert showing control tokens by default

* feat: revert changes to default behavior of llama_token_to_piece; provide overridden declaration to receive "bool special" param to toggle showing control tokens

* feat: use the overridden declaration of llama_token_to_piece from common/common.cpp to specify "false" so that control tokens are not shown in chat completion responses"

* common : simplify

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Kyle Mistele 2024-04-24 05:15:29 -05:00 • committed by GitHub
parent 28103f4832
commit 37246b1031
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 7 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

6
common/common.cpp
View file

@ -2328,12 +2328,12 @@ std::vector<llama_token> llama_tokenize(
return result;
}
std::string llama_token_to_piece(const struct llama_context * ctx, llama_token token) {
std::string llama_token_to_piece(const struct llama_context * ctx, llama_token token, bool special) {
std::vector<char> result(8, 0);
const int n_tokens = llama_token_to_piece(llama_get_model(ctx), token, result.data(), result.size(), true);
const int n_tokens = llama_token_to_piece(llama_get_model(ctx), token, result.data(), result.size(), special);
if (n_tokens < 0) {
result.resize(-n_tokens);
int check = llama_token_to_piece(llama_get_model(ctx), token, result.data(), result.size(), true);
int check = llama_token_to_piece(llama_get_model(ctx), token, result.data(), result.size(), special);
GGML_ASSERT(check == -n_tokens);
} else {
result.resize(n_tokens);