]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
model : add Jina Embeddings v5 Nano (partial EuroBERT) support (#19826)
authorMaximilian Werk <redacted>
Thu, 26 Feb 2026 11:14:09 +0000 (12:14 +0100)
committerGitHub <redacted>
Thu, 26 Feb 2026 11:14:09 +0000 (12:14 +0100)
commit66287bdaaca3042bd4df5fc8f7bd4d58bfcd208c
treeb31d44395a63e43863b1cddb017310ba6d554174
parent1ca3d1de153152645cf890b637c2c6450f1615e3
model : add Jina Embeddings v5 Nano (partial EuroBERT) support (#19826)

* WIP: Add EuroBERT support with autoformatting changes

This commit includes:
- EuroBERT model implementation for GGUF conversion
- C++ backend support for EuroBERT architecture
- Unintended autoformatting changes to Python files

Saving before reverting formatting-only changes.

* feat: add back eos assert when not last token pooling

* feat: removed duplicated code and cleanup

* feat: removed not working architectures and unnecessary check

* fix: typo

* fix: dynamic pooling config

* feat: added an example model for eurobert

* feat: proper llama-vocab implementation for jina-v5

* fix: removed unnecessary comments
12 files changed:
convert_hf_to_gguf.py
convert_hf_to_gguf_update.py
gguf-py/gguf/constants.py
src/CMakeLists.txt
src/llama-arch.cpp
src/llama-arch.h
src/llama-model.cpp
src/llama-vocab.cpp
src/models/eurobert.cpp [new file with mode: 0644]
src/models/models.h
tests/test-tokenizer-0.sh
tools/imatrix/imatrix.cpp