]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama : add Deepseek MoE v1 & GigaChat models (#10827)
authorValentin Mamedov <redacted>
Sun, 15 Dec 2024 17:02:46 +0000 (00:02 +0700)
committerGitHub <redacted>
Sun, 15 Dec 2024 17:02:46 +0000 (19:02 +0200)
commita0974156f334acf8af5858d7ede5ab7d7490d415
tree237b52de6913fbf80aa1726506a90b3e79a69dc6
parent87cf323cef80f6aa530f047ab05b539ebc6b7e3c
llama : add Deepseek MoE v1 & GigaChat models (#10827)

* Add deepseek v1 arch & gigachat template

* improve template code

* add readme

* delete comments

* remove comment

* fix format

* lint llama.cpp

* fix order of deepseek and deepseek2, move gigachat temlate to the end of func

* fix order of deepseek and deepseek2 in constants; mark shared exp as deepseek arch need

* remove comments

* move deepseek above deepseek2

* change placement of gigachat chat template
README.md
convert_hf_to_gguf.py
convert_hf_to_gguf_update.py
gguf-py/gguf/constants.py
gguf-py/gguf/tensor_mapping.py
src/llama.cpp
tests/test-chat-template.cpp