vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fix phi3 chat template confusion with zephyr (#7449)

Browse source 
* Fix phi3 template matching vs zephyr

* Add regression test for new phi3 chat template

* Implement review suggestions

* Fix phi3 jinja test templates & match by <|end|>

* Apply suggestion

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>

* Add all phi3 template variants in tests

* Remove unneeded message trimming

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>

* Fix tests to not expect trimmed messages

---------

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
This commit is contained in:
Tristan Druyen 2024-05-23 16:15:15 +02:00 • committed by GitHub
parent 8b94e799df
commit 007489e895
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 25 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

18
llama.cpp
View file

@ -17852,6 +17852,15 @@ static int32_t llama_chat_apply_template_internal(
}
}
// llama2 templates seem to not care about "add_generation_prompt"
} else if (tmpl == "phi3" || (tmpl.find("<|assistant|>") != std::string::npos && tmpl.find("<|end|>") != std::string::npos)) {
// Phi 3
for (auto message : chat) {
std::string role(message->role);
ss << "<|" << role << "|>\n" << message->content << "<|end|>\n";
}
if (add_ass) {
ss << "<|assistant|>\n";
}
} else if (tmpl == "zephyr" || tmpl.find("<|user|>") != std::string::npos) {
// zephyr template
for (auto message : chat) {
@ -17984,15 +17993,6 @@ static int32_t llama_chat_apply_template_internal(
if (add_ass) {
ss << "<|start_header_id|>assistant<|end_header_id|>\n\n";
}
} else if (tmpl == "phi3" || (tmpl.find("<|assistant|>") != std::string::npos && tmpl.find("<|end|>") != std::string::npos )) {
// Phi 3
for (auto message : chat) {
std::string role(message->role);
ss << "<|" << role << "|>\n" << trim(message->content) << "<|end|>\n";
}
if (add_ass) {
ss << "<|assistant|>\n";
}
} else {
// template not supported
return -1;