From 0974ad7a7cd4bca846b15c484ff3be890135a52c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sigbj=C3=B8rn=20Skj=C3=A6ret?= Date: Sat, 7 Jun 2025 14:13:12 +0200 Subject: [PATCH] llama : fix llama_model_chat_template with template name (LLM_KV with suffix) (#14050) --- src/llama-arch.cpp | 11 ++++++++--- src/llama-arch.h | 1 - src/llama-model.cpp | 2 +- 3 files changed, 9 insertions(+), 5 deletions(-) diff --git a/src/llama-arch.cpp b/src/llama-arch.cpp index c0590e105..43fa60a80 100644 --- a/src/llama-arch.cpp +++ b/src/llama-arch.cpp @@ -200,7 +200,6 @@ static const std::map LLM_KV_NAMES = { { LLM_KV_TOKENIZER_HF_JSON, "tokenizer.huggingface.json" }, { LLM_KV_TOKENIZER_RWKV, "tokenizer.rwkv.world" }, { LLM_KV_TOKENIZER_CHAT_TEMPLATE, "tokenizer.chat_template" }, - { LLM_KV_TOKENIZER_CHAT_TEMPLATE_N, "tokenizer.chat_template.%s" }, { LLM_KV_TOKENIZER_FIM_PRE_ID, "tokenizer.ggml.fim_pre_token_id" }, { LLM_KV_TOKENIZER_FIM_SUF_ID, "tokenizer.ggml.fim_suf_token_id" }, { LLM_KV_TOKENIZER_FIM_MID_ID, "tokenizer.ggml.fim_mid_token_id" }, @@ -1707,8 +1706,14 @@ static const std::map LLM_TENSOR_INFOS = { LLM_KV::LLM_KV(llm_arch arch, const char * suffix) : arch(arch), suffix(suffix) {} std::string LLM_KV::operator()(llm_kv kv) const { - return suffix ? ::format(LLM_KV_NAMES.at(kv), LLM_ARCH_NAMES.at(arch), suffix) - : ::format(LLM_KV_NAMES.at(kv), LLM_ARCH_NAMES.at(arch)); + std::string name = ::format(LLM_KV_NAMES.at(kv), LLM_ARCH_NAMES.at(arch)); + + if (suffix != nullptr) { + name += "."; + name += suffix; + } + + return name; } std::string LLM_TN_IMPL::str() const { diff --git a/src/llama-arch.h b/src/llama-arch.h index 930cb4eca..f3825528a 100644 --- a/src/llama-arch.h +++ b/src/llama-arch.h @@ -196,7 +196,6 @@ enum llm_kv { LLM_KV_TOKENIZER_HF_JSON, LLM_KV_TOKENIZER_RWKV, LLM_KV_TOKENIZER_CHAT_TEMPLATE, - LLM_KV_TOKENIZER_CHAT_TEMPLATE_N, LLM_KV_TOKENIZER_FIM_PRE_ID, LLM_KV_TOKENIZER_FIM_SUF_ID, LLM_KV_TOKENIZER_FIM_MID_ID, diff --git a/src/llama-model.cpp b/src/llama-model.cpp index 915d5a927..c41ee2450 100644 --- a/src/llama-model.cpp +++ b/src/llama-model.cpp @@ -13788,7 +13788,7 @@ uint64_t llama_model_size(const llama_model * model) { } const char * llama_model_chat_template(const llama_model * model, const char * name) { - const auto key = name ? LLM_KV(model->arch, name)(LLM_KV_TOKENIZER_CHAT_TEMPLATE_N) + const auto key = name ? LLM_KV(model->arch, name)(LLM_KV_TOKENIZER_CHAT_TEMPLATE) : LLM_KV(model->arch)(LLM_KV_TOKENIZER_CHAT_TEMPLATE); const auto & it = model->gguf_kv.find(key); if (it == model->gguf_kv.end()) {