tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-09-08 08:23:20 -04:00
Code Issues Packages Projects Releases Wiki Activity

serverinfill tokens correction

Browse Source
This commit is contained in:
vvhg1
2023-10-06 18:35:50 +02:00
parent 8bd24b2e5c
commit 6796e7450c
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
examples/server/server.cpp
View File

@@ -344,9 +344,10 @@ struct llama_server_context
void loadInfill()
{
auto prefix_tokens = tokenize(params.input_prefix, true); // always add BOS
auto suffix_tokens = tokenize(params.input_suffix, true); // always add BOS
auto prefix_tokens = tokenize(params.input_prefix, false);
auto suffix_tokens = tokenize(params.input_suffix, false);
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));
prefix_tokens.insert(prefix_tokens.end(), suffix_tokens.begin(), suffix_tokens.end());
prefix_tokens.push_back(llama_token_middle(ctx));