CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

rerank : use [SEP] token instead of [BOS] (#9737)

Browse Source 
* rerank : use [SEP] token instead of [BOS]

ggml-ci

* common : sanity check for non-NULL tokens

ggml-ci

* ci : adjust rank score interval

ggml-ci

* ci : add shebang to run.sh

ggml-ci
This commit is contained in:
Georgi Gerganov
2024-10-05 15:55:04 +03:00
committed by GitHub
parent 58b16695e1
commit 8c475b97b8
5 changed files with 45 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/server/server.cpp
View File

@@ -2027,7 +2027,7 @@ struct server_context {
continue;
}
// prompt: <s>query</s><s>doc</s>
// prompt: [BOS]query[EOS][SEP]doc[EOS]
prompt_tokens.clear();
prompt_tokens.push_back(llama_token_bos(model));
{
@@ -2035,7 +2035,7 @@ struct server_context {
prompt_tokens.insert(prompt_tokens.end(), part.begin(), part.end());
}
prompt_tokens.push_back(llama_token_eos(model));
prompt_tokens.push_back(llama_token_bos(model));
prompt_tokens.push_back(llama_token_sep(model));
{
const auto part = tokenize(slot.prompt[1], false);
prompt_tokens.insert(prompt_tokens.end(), part.begin(), part.end());