]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 3a9cb4c)
llama : add llama_chat_apply_template() (#5538)
authorXuan Son Nguyen <redacted>
Mon, 19 Feb 2024 08:23:37 +0000 (09:23 +0100)
committerGitHub <redacted>
Mon, 19 Feb 2024 08:23:37 +0000 (10:23 +0200)
commit11b12de39bd787c0494da0cd405958fdfedc29c4
treef1e5e999a6b01d84bf4852be77cccdbfe1668c79tree
parent3a9cb4ca6408c29423373dd6cd7aa78a58286c00commit | diff
llama : add llama_chat_apply_template() (#5538)

* llama: add llama_chat_apply_template

* test-chat-template: remove dedundant vector

* chat_template: do not use std::string for buffer

* add clarification for llama_chat_apply_template

* llama_chat_apply_template: add zephyr template

* llama_chat_apply_template: correct docs

* llama_chat_apply_template: use term "chat" everywhere

* llama_chat_apply_template: change variable name to "tmpl"
Makefile diff | blob | history
llama.cpp diff | blob | history
llama.h diff | blob | history
tests/CMakeLists.txt diff | blob | history
tests/test-chat-template.cpp [new file with mode: 0644] blob
Packaging of ggml-org/llama.cpp