vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/nix/package.nix
#	CMakePresets.json
#	README.md
#	flake.lock
#	ggml/src/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
This commit is contained in:
Concedo 2024-07-02 21:05:45 +08:00
commit 0fc18d2d82
25 changed files with 1452 additions and 1367 deletions
Download patch file Download diff file Expand all files Collapse all files

11
examples/main/main.cpp
View file

@ -262,7 +262,7 @@ int main(int argc, char ** argv) {
std::vector<llama_token> embd_inp;
{
auto prompt = params.conversation
auto prompt = (params.conversation && params.enable_chat_template)
? chat_add_and_format(model, chat_msgs, "system", params.prompt) // format the system prompt in conversation mode
: params.prompt;
if (params.interactive_first || !params.prompt.empty() || session_tokens.empty()) {
@ -811,7 +811,9 @@ int main(int argc, char ** argv) {
is_antiprompt = true;
}
chat_add_and_format(model, chat_msgs, "assistant", assistant_ss.str());
if (params.enable_chat_template) {
chat_add_and_format(model, chat_msgs, "assistant", assistant_ss.str());
}
is_interacting = true;
printf("\n");
}
@ -873,12 +875,13 @@ int main(int argc, char ** argv) {
string_process_escapes(buffer);
}
std::string user_inp = params.conversation
bool format_chat = params.conversation && params.enable_chat_template;
std::string user_inp = format_chat
? chat_add_and_format(model, chat_msgs, "user", std::move(buffer))
: std::move(buffer);
// TODO: one inconvenient of current chat template implementation is that we can't distinguish between user input and special tokens (prefix/postfix)
const auto line_pfx = ::llama_tokenize(ctx, params.input_prefix, false, true);
const auto line_inp = ::llama_tokenize(ctx, user_inp, false, params.conversation);
const auto line_inp = ::llama_tokenize(ctx, user_inp, false, format_chat);
const auto line_sfx = ::llama_tokenize(ctx, params.input_suffix, false, true);
LOG("input tokens: %s\n", LOG_TOKENS_TOSTR_PRETTY(ctx, line_inp).c_str());