root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 11:24:35 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

server : apply fix from #3722

Browse Source
This commit is contained in:
Georgi Gerganov 2023-10-22 21:05:45 +03:00
parent 00ae55b388
commit 8fe7ca4875
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
examples/server/server.cpp
View File

@ -1539,10 +1539,12 @@ struct llama_server_context
}
auto prefix_tokens = tokenize(slot.params.input_prefix, false);
auto suffix_tokens = tokenize(slot.params.input_suffix, false);
const int space_token = 29871;
if (suff_rm_leading_spc && suffix_tokens[0] == space_token) {
const int space_token = 29871; // TODO: this should not be hardcoded
if (suff_rm_leading_spc && !suffix_tokens.empty() && suffix_tokens[0] == space_token) {
suffix_tokens.erase(suffix_tokens.begin());
}
prefix_tokens.insert(prefix_tokens.begin(), llama_token_prefix(ctx));
prefix_tokens.insert(prefix_tokens.begin(), llama_token_bos(ctx)); // always add BOS
prefix_tokens.insert(prefix_tokens.end(), llama_token_suffix(ctx));