# BGE-Reranker-v2-m3 for LocalAI (llama-cpp / cuda13-llama-cpp backend).
# Copy to /data/apps/localai/models/bge-reranker-v2-m3-FP16.gguf.yaml after GGUF download.
#
# GGUF: bge-reranker-v2-m3-FP16.gguf (~1.1 GB) in same directory as this YAML.
# API id: bge-reranker-v2-m3-FP16.gguf
# Endpoint: POST /v1/rerank
#
# Do NOT use backend: rerankers for GGUF — that backend is for HuggingFace transformers.
# cuda13-llama-cpp is selected automatically on the cuda-13 image when backend: llama-cpp.

name: bge-reranker-v2-m3-FP16.gguf
backend: llama-cpp
reranking: true
embeddings: false
description: BGE-Reranker-v2-m3 cross-encoder (FP16 GGUF)
known_usecases:
  - rerank
parameters:
  model: bge-reranker-v2-m3-FP16.gguf
context_size: 8192
template:
  use_tokenizer_template: true
function:
  grammar:
    disable: true
options:
  - use_jinja:true