mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-07-28 13:20:27 -04:00
chat : fix kimi-k2 chat template (#14852)
This commit is contained in:
committed by
Aaron Teo
parent
07a49304ad
commit
c1d4ffc553
@@ -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_ARCH_UNKNOWN,
|
||||
{
|
||||
{ LLM_TENSOR_TOKEN_EMBD, "token_embd" },
|
||||
},
|
||||
},
|
||||
{
|
||||
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_ARCH_UNKNOWN,
|
||||
{
|
||||
{ LLM_TENSOR_TOKEN_EMBD, "token_embd" },
|
||||
},
|
||||
},
|
||||
};
|
||||
|
||||
static const std::map<llm_tensor, llm_tensor_info> LLM_TENSOR_INFOS = {
|
||||
|
@@ -718,11 +718,10 @@ int32_t llm_chat_apply_template(
|
||||
}
|
||||
|
||||
ss << message->content << "<|im_end|>";
|
||||
|
||||
}
|
||||
if (add_ass) {
|
||||
ss << "<|im_assistant|>assistant<|im_middle|>";
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// template not supported
|
||||
return -1;
|
||||
|
Reference in New Issue
Block a user