tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-28 13:20:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

chat : fix kimi-k2 chat template (#14852)

Browse Source
This commit is contained in:
Xuan-Son Nguyen
2025-07-24 13:59:56 +02:00
committed by Aaron Teo
parent 07a49304ad
commit c1d4ffc553
2 changed files with 9 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
src/llama-arch.cpp
View File

@@ -1933,12 +1933,6 @@ static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_N
{ LLM_TENSOR_TOKEN_EMBD_NORM, "token_embd_norm" }, { LLM_TENSOR_TOKEN_EMBD_NORM, "token_embd_norm" },
} }
}, },
{
LLM_ARCH_UNKNOWN,
{
{ LLM_TENSOR_TOKEN_EMBD, "token_embd" },
},
},
{ {
LLM_ARCH_DREAM, LLM_ARCH_DREAM,
{ {
@@ -1956,6 +1950,12 @@ static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_N
{ LLM_TENSOR_FFN_UP, "blk.%d.ffn_up" }, { LLM_TENSOR_FFN_UP, "blk.%d.ffn_up" },
}, },
}, },
{
LLM_ARCH_UNKNOWN,
{
{ LLM_TENSOR_TOKEN_EMBD, "token_embd" },
},
},
}; };
static const std::map<llm_tensor, llm_tensor_info> LLM_TENSOR_INFOS = { static const std::map<llm_tensor, llm_tensor_info> LLM_TENSOR_INFOS = {

7
src/llama-chat.cpp
View File

@@ -718,10 +718,9 @@ int32_t llm_chat_apply_template(
} }
ss << message->content << "<|im_end|>"; ss << message->content << "<|im_end|>";
}
if (add_ass) { if (add_ass) {
ss << "<|im_assistant|>assistant<|im_middle|>"; ss << "<|im_assistant|>assistant<|im_middle|>";
}
} }
} else { } else {
// template not supported // template not supported