]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
model : support for LlamaBidirectionalModel architecture (#18220)
authorSaba Fallah <redacted>
Wed, 24 Dec 2025 13:02:36 +0000 (14:02 +0100)
committerGitHub <redacted>
Wed, 24 Dec 2025 13:02:36 +0000 (14:02 +0100)
commit54132f1b1fa16b419d589ac03d3266178259eb25
treeb003a2513e0c6e788e653222d516e84837fa126e
parent2a9ea2020c6d2bfe243ecd63f3c564babccc2004
model : support for LlamaBidirectionalModel architecture (#18220)

* model: llama-embed-nemotron

* minor: python lint

* changed arch-name

* templated llm_build_llama to be used for both llama and llama-embed arch
convert_hf_to_gguf.py
gguf-py/gguf/constants.py
src/llama-arch.cpp
src/llama-arch.h
src/llama-model.cpp
src/models/llama.cpp
src/models/models.h