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

model : add hunyuan dense (#14878)

Browse source 
* support hunyuan_v1_dense

Signed-off-by: stevenkuang <stevenkuang@tencent.com>

* update hunyuan_moe to hunyuan_v1_moe

Signed-off-by: stevenkuang <stevenkuang@tencent.com>

* fix rope alpha assert and bos token

Signed-off-by: stevenkuang <stevenkuang@tencent.com>

* add blank line

Signed-off-by: stevenkuang <stevenkuang@tencent.com>

* Revert "update hunyuan_moe to hunyuan_v1_moe"

This reverts commit aa973ca21913aba77f6e81a935270ef7be222e75.

* use hunyuan_dense instead of hunyuan_v1_dense

Signed-off-by: stevenkuang <stevenkuang@tencent.com>

* fix hunyuan_moe chat template

Signed-off-by: stevenkuang <stevenkuang@tencent.com>

* remove leftover code

Signed-off-by: stevenkuang <stevenkuang@tencent.com>

* update hunyuan dense chat template

Signed-off-by: stevenkuang <stevenkuang@tencent.com>

* fix hunyuan dense vocab and chat template

Signed-off-by: stevenkuang <stevenkuang@tencent.com>

---------

Signed-off-by: stevenkuang <stevenkuang@tencent.com>
This commit is contained in:
stevenkuang 2025-08-01 21:31:12 +08:00 • committed by GitHub
parent 1c872f71fb
commit 0f5ccd6fd1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 351 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

21
src/llama-chat.cpp
View file

@ -66,6 +66,7 @@ static const std::map<std::string, llm_chat_template> LLM_CHAT_TEMPLATES = {
{ "llama4", LLM_CHAT_TEMPLATE_LLAMA4 },
{ "smolvlm", LLM_CHAT_TEMPLATE_SMOLVLM },
{ "hunyuan-moe", LLM_CHAT_TEMPLATE_HUNYUAN_MOE },
{ "hunyuan-dense", LLM_CHAT_TEMPLATE_HUNYUAN_DENSE },
{ "kimi-k2", LLM_CHAT_TEMPLATE_KIMI_K2 },
};
@ -193,6 +194,8 @@ llm_chat_template llm_chat_detect_template(const std::string & tmpl) {
return LLM_CHAT_TEMPLATE_DOTS1;
} else if (tmpl_contains("<|startoftext|>") && tmpl_contains("<|extra_4|>")) {
return LLM_CHAT_TEMPLATE_HUNYUAN_MOE;
} else if (tmpl_contains("<｜hy_place▁holder▁no▁2｜>") && tmpl_contains("<｜hy_place▁holder▁no▁3｜>")) {
return LLM_CHAT_TEMPLATE_HUNYUAN_DENSE;
} else if (tmpl_contains("<|im_assistant|>assistant<|im_middle|>")) {
return LLM_CHAT_TEMPLATE_KIMI_K2;
}
@ -698,11 +701,27 @@ int32_t llm_chat_apply_template(
if (role == "system") {
ss << "<|startoftext|>" << message->content << "<|extra_4|>";
} else if (role == "assistant") {
ss << "<|startoftext|>" << message->content << "<|eos|>";
ss << message->content << "<|eos|>";
} else {
ss << "<|startoftext|>" << message->content << "<|extra_0|>";
}
}
} else if (tmpl == LLM_CHAT_TEMPLATE_HUNYUAN_DENSE) {
// tencent/Hunyuan-4B-Instruct
for (size_t i = 0; i < chat.size(); i++) {
std::string role(chat[i]->role);
if (i == 0) {
if (role == "system") {
ss << chat[i]->content << "<｜hy_place▁holder▁no▁3｜>";
}
}
if (role == "assistant") {
ss << "<｜hy_Assistant｜>" << chat[i]->content << "<｜hy_place▁holder▁no▁2｜>";
} else if (role == "user") {
ss << "<｜hy_User｜>" << chat[i]->content << "<｜hy_Assistant｜>";
}
}
} else if (tmpl == LLM_CHAT_TEMPLATE_KIMI_K2) {
// moonshotai/Kimi-K2-Instruct
for (auto message : chat) {