metadata

base_model: BAAI/bge-reranker-base
language:
  - en
  - zh
library_name: sentence-transformers
license: mit
pipeline_tag: text-ranking
tags:
  - mteb
  - text-embeddings-inference
  - llama-cpp
  - gguf-my-repo
model-index:
  - name: bge-reranker-base
    results:
      - task:
          type: Reranking
        dataset:
          name: MTEB CMedQAv1
          type: C-MTEB/CMedQAv1-reranking
          config: default
          split: test
          revision: None
        metrics:
          - type: map
            value: 81.27206722525007
          - type: mrr
            value: 84.14238095238095
      - task:
          type: Reranking
        dataset:
          name: MTEB CMedQAv2
          type: C-MTEB/CMedQAv2-reranking
          config: default
          split: test
          revision: None
        metrics:
          - type: map
            value: 84.10369934291236
          - type: mrr
            value: 86.79376984126984
      - task:
          type: Reranking
        dataset:
          name: MTEB MMarcoReranking
          type: C-MTEB/Mmarco-reranking
          config: default
          split: dev
          revision: None
        metrics:
          - type: map
            value: 35.4600511272538
          - type: mrr
            value: 34.60238095238095
      - task:
          type: Reranking
        dataset:
          name: MTEB T2Reranking
          type: C-MTEB/T2Reranking
          config: default
          split: dev
          revision: None
        metrics:
          - type: map
            value: 67.27728847727172
          - type: mrr
            value: 77.1315192743764

sabafallah/bge-reranker-base-Q4_K_M-GGUF

This model was converted to GGUF format from BAAI/bge-reranker-base using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo sabafallah/bge-reranker-base-Q4_K_M-GGUF --hf-file bge-reranker-base-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo sabafallah/bge-reranker-base-Q4_K_M-GGUF --hf-file bge-reranker-base-q4_k_m.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo sabafallah/bge-reranker-base-Q4_K_M-GGUF --hf-file bge-reranker-base-q4_k_m.gguf -p "The meaning to life and the universe is"

./llama-server --hf-repo sabafallah/bge-reranker-base-Q4_K_M-GGUF --hf-file bge-reranker-base-q4_k_m.gguf -c 2048