]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
model : add NeoBERT (#14164)
authorĐinh Trọng Huy <redacted>
Mon, 16 Jun 2025 12:53:41 +0000 (21:53 +0900)
committerGitHub <redacted>
Mon, 16 Jun 2025 12:53:41 +0000 (14:53 +0200)
commitad590be98c83217fcf1a101d78d9ab389fd5dc0b
treefdfbb6dd80358d0ab3fe1ea20d8e75acf7041f67
parent7d6d91babfa129906b39c9099eca4234c44f4f1e
model : add NeoBERT (#14164)

* convert neobert model to gguf

* add inference graph

* fix flake8 lint

* followed reviewer suggestions

Co-authored-by: Georgi Gerganov <redacted>
* follow reviewers suggestions

Co-authored-by: Georgi Gerganov <redacted>
* override NeoBERT feed-forward length

---------

Co-authored-by: dinhhuy <redacted>
Co-authored-by: Georgi Gerganov <redacted>
convert_hf_to_gguf.py
gguf-py/gguf/constants.py
gguf-py/gguf/tensor_mapping.py
src/llama-arch.cpp
src/llama-arch.h
src/llama-model.cpp