diff --git a/src/llmtuner/data/template.py b/src/llmtuner/data/template.py index 6cc12c56..88d7cb86 100644 --- a/src/llmtuner/data/template.py +++ b/src/llmtuner/data/template.py @@ -773,3 +773,11 @@ _register_template( format_user=StringFormatter(slots=[":{{content}}\n:"]), format_separator=EmptyFormatter(slots=["\n"]), ) + +_register_template( + name="breeze", + format_user=StringFormatter(slots=["[INST] {{content}} [/INST] "]), + format_system=StringFormatter(slots=[{"bos_token"}, "{{content}}"]), + default_system="You are a helpful AI assistant built by MediaTek Research. The user you are helping speaks Traditional Chinese and comes from Taiwan. ", + efficient_eos=True, +) diff --git a/src/llmtuner/extras/constants.py b/src/llmtuner/extras/constants.py index 2c7f5e5f..38fde712 100644 --- a/src/llmtuner/extras/constants.py +++ b/src/llmtuner/extras/constants.py @@ -981,3 +981,17 @@ register_model_group( }, template="atom", ) + +register_model_group( + models={ + "Breeze-7B": { + DownloadSource.DEFAULT: "MediaTek-Research/Breeze-7B-Base-v1_0", + DownloadSource.MODELSCOPE: "MediaTek-Research/Breeze-7B-Base-v1_0", + }, + "Breeze-7B-Chat": { + DownloadSource.DEFAULT: "MediaTek-Research/Breeze-7B-Instruct-v1_0", + DownloadSource.MODELSCOPE: "MediaTek-Research/Breeze-7B-Instruct-v1_0", + } + }, + template="breeze", +)