CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-28 08:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

model : add support for Seed-OSS (#15490)

Browse Source 
* First draft

* Fix linter errors

* Added missing sinks nullptr

* Don't forget the llama-arch!

* We're through to the generation stage.

* Fix post-attention norm

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Fix RoPE type

* Fix tensor name and reorder llm_types

* Update gguf-py/gguf/constants.py

Remove nonexistent FFN_POST_NORM tensor

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.h

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Add basic chat template

* Add chat template tests

* Remake chat template test

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-chat.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Reorder llm type descriptions

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Piotr Wilkin (ilintar)
2025-08-23 15:21:52 +02:00
committed by GitHub
parent 9ef536907d
commit b1afcab804
9 changed files with 244 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
src/llama-chat.cpp
View File

@@ -69,6 +69,7 @@ static const std::map<std::string, llm_chat_template> LLM_CHAT_TEMPLATES = {
{ "gpt-oss", LLM_CHAT_TEMPLATE_OPENAI_MOE },
{ "hunyuan-dense", LLM_CHAT_TEMPLATE_HUNYUAN_DENSE },
{ "kimi-k2", LLM_CHAT_TEMPLATE_KIMI_K2 },
{ "seed_oss", LLM_CHAT_TEMPLATE_SEED_OSS },
};
llm_chat_template llm_chat_template_from_str(const std::string & name) {
@@ -201,6 +202,8 @@ llm_chat_template llm_chat_detect_template(const std::string & tmpl) {
return LLM_CHAT_TEMPLATE_HUNYUAN_DENSE;
} else if (tmpl_contains("<|im_assistant|>assistant<|im_middle|>")) {
return LLM_CHAT_TEMPLATE_KIMI_K2;
} else if (tmpl_contains("<seed:bos>")) {
return LLM_CHAT_TEMPLATE_SEED_OSS;
}
return LLM_CHAT_TEMPLATE_UNKNOWN;
}
@@ -752,6 +755,14 @@ int32_t llm_chat_apply_template(
if (add_ass) {
ss << "<|im_assistant|>assistant<|im_middle|>";
}
} else if (tmpl == LLM_CHAT_TEMPLATE_SEED_OSS) {
for (auto message: chat) {
std::string role(message->role);
ss << "<seed:bos>" << role << "\n" << (role == "assistant" ? trim(message->content) : message->content) << "<seed:eos>";
}
if (add_ass) {
ss << "<seed:bos>assistant\n";
}
} else {
// template not supported
return -1;