From 9c405c9f9a7cfd23511fd6b2de05dc72481119b4 Mon Sep 17 00:00:00 2001 From: Xuan Son Nguyen Date: Tue, 20 Feb 2024 15:58:27 +0100 Subject: Server: use llama_chat_apply_template (#5593) * server: use llama_chat_apply_template * server: remove trailing space * server: fix format_chat * server: fix help message Co-authored-by: Georgi Gerganov * server: fix formatted_chat --------- Co-authored-by: Georgi Gerganov --- llama.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'llama.cpp') diff --git a/llama.cpp b/llama.cpp index 5de07dfa..4296eca3 100644 --- a/llama.cpp +++ b/llama.cpp @@ -12602,7 +12602,7 @@ LLAMA_API int32_t llama_chat_apply_template( // load template from model std::vector model_template(2048, 0); // longest known template is about 1200 bytes std::string template_key = "tokenizer.chat_template"; - int32_t res = llama_model_meta_val_str(model, template_key.c_str(), model_template.data(), curr_tmpl.size()); + int32_t res = llama_model_meta_val_str(model, template_key.c_str(), model_template.data(), model_template.size()); if (res < 0) { // worst case: there is no information about template, we will use chatml by default curr_tmpl = "<|im_start|>"; // see llama_chat_apply_template_internal -- cgit v1.2.3