]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
model : detect GigaChat3-10-A1.8B as deepseek lite (#17420)
authorubergarm <redacted>
Fri, 21 Nov 2025 13:51:38 +0000 (08:51 -0500)
committerGitHub <redacted>
Fri, 21 Nov 2025 13:51:38 +0000 (14:51 +0100)
commit23bc779a6e58762ea892eca1801b2ea1b9050c00
tree1aa8297cc21ffd53ea6269b233a254603f754f77
parent28175f857d21f7acb9bd060d61d8b073219fe59c
model : detect GigaChat3-10-A1.8B as deepseek lite (#17420)

* Detect GigaChat3-10-A1.8B as deepseek lite

Hardcodes checking number of layers to detect if lite version of deepseek.

* Add commnent identifying deepseek lite variants

deepseek lite variants include DeepSeek-V2-Lite, GigaChat3-10B-A1.8B
src/llama-model.cpp
src/models/deepseek2.cpp