Skip to content

Refactor chat template API #6822

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 11 commits into
base: master
Choose a base branch
from
Draft

Refactor chat template API #6822

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
d6df8ec
refactor chat template api
ngxson Apr 22, 2024
98c46cf
fix llama_chat_apply_template
ngxson Apr 22, 2024
a202b56
add header
ngxson Apr 22, 2024
588b72d
fix templates not support system message
ngxson Apr 24, 2024
f1a9354
clean up
ngxson Apr 24, 2024
3222b4b
add guide for adding template
ngxson Apr 24, 2024
ada5429
Merge branch 'master' into xsn/chat_template_prefix_postfix
ngxson Apr 24, 2024
81b5903
adapt phi3 template
ngxson Apr 24, 2024
0d3363e
llama_chat_get_typed_template
ngxson Apr 24, 2024
7f89803
add enum keyword
ngxson Apr 24, 2024
476d319
correct buffer size
ngxson Apr 24, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion examples/server/utils.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -149,7 +149,7 @@ inline std::string format_chat(const struct llama_model * model, const std::stri
res = llama_chat_apply_template(model, ptr_tmpl, chat.data(), chat.size(), true, buf.data(), buf.size());
}

const std::string formatted_chat(buf.data(), res);
const std::string formatted_chat(buf.data());

LOG_VERBOSE("formatted_chat", {{"text", formatted_chat.c_str()}});

Expand Down
Loading
Loading