---
language:
- en
license: apache-2.0
tags:
- sentence-transformers
- cross-encoder
- reranker
- generated_from_trainer
- dataset_size:143393475
- loss:MSELoss
- llama-cpp
- gguf-my-repo
base_model: cross-encoder/ettin-reranker-150m-v1
pipeline_tag: text-ranking
library_name: sentence-transformers
metrics:
- map
- mrr@10
- ndcg@10
model-index:
- name: ettin-reranker-150m-v1
  results:
  - task:
      type: cross-encoder-reranking
      name: Cross Encoder Reranking
    dataset:
      name: NanoMSMARCO R100
      type: NanoMSMARCO_R100
    metrics:
    - type: map
      value: 0.6425
      name: Map
    - type: mrr@10
      value: 0.6459
      name: Mrr@10
    - type: ndcg@10
      value: 0.7243
      name: Ndcg@10
  - task:
      type: cross-encoder-reranking
      name: Cross Encoder Reranking
    dataset:
      name: NanoNFCorpus R100
      type: NanoNFCorpus_R100
    metrics:
    - type: map
      value: 0.3657
      name: Map
    - type: mrr@10
      value: 0.5762
      name: Mrr@10
    - type: ndcg@10
      value: 0.4067
      name: Ndcg@10
  - task:
      type: cross-encoder-reranking
      name: Cross Encoder Reranking
    dataset:
      name: NanoNQ R100
      type: NanoNQ_R100
    metrics:
    - type: map
      value: 0.7484
      name: Map
    - type: mrr@10
      value: 0.7678
      name: Mrr@10
    - type: ndcg@10
      value: 0.7992
      name: Ndcg@10
  - task:
      type: cross-encoder-reranking
      name: Cross Encoder Reranking
    dataset:
      name: NanoFiQA2018 R100
      type: NanoFiQA2018_R100
    metrics:
    - type: map
      value: 0.563
      name: Map
    - type: mrr@10
      value: 0.6733
      name: Mrr@10
    - type: ndcg@10
      value: 0.6127
      name: Ndcg@10
  - task:
      type: cross-encoder-reranking
      name: Cross Encoder Reranking
    dataset:
      name: NanoTouche2020 R100
      type: NanoTouche2020_R100
    metrics:
    - type: map
      value: 0.472
      name: Map
    - type: mrr@10
      value: 0.8155
      name: Mrr@10
    - type: ndcg@10
      value: 0.5518
      name: Ndcg@10
  - task:
      type: cross-encoder-reranking
      name: Cross Encoder Reranking
    dataset:
      name: NanoSciFact R100
      type: NanoSciFact_R100
    metrics:
    - type: map
      value: 0.716
      name: Map
    - type: mrr@10
      value: 0.713
      name: Mrr@10
    - type: ndcg@10
      value: 0.7613
      name: Ndcg@10
  - task:
      type: cross-encoder-reranking
      name: Cross Encoder Reranking
    dataset:
      name: NanoHotpotQA R100
      type: NanoHotpotQA_R100
    metrics:
    - type: map
      value: 0.9307
      name: Map
    - type: mrr@10
      value: 1.0
      name: Mrr@10
    - type: ndcg@10
      value: 0.9573
      name: Ndcg@10
  - task:
      type: cross-encoder-reranking
      name: Cross Encoder Reranking
    dataset:
      name: NanoArguAna R100
      type: NanoArguAna_R100
    metrics:
    - type: map
      value: 0.6597
      name: Map
    - type: mrr@10
      value: 0.6579
      name: Mrr@10
    - type: ndcg@10
      value: 0.7375
      name: Ndcg@10
  - task:
      type: cross-encoder-reranking
      name: Cross Encoder Reranking
    dataset:
      name: NanoFEVER R100
      type: NanoFEVER_R100
    metrics:
    - type: map
      value: 0.9436
      name: Map
    - type: mrr@10
      value: 0.975
      name: Mrr@10
    - type: ndcg@10
      value: 0.96
      name: Ndcg@10
  - task:
      type: cross-encoder-reranking
      name: Cross Encoder Reranking
    dataset:
      name: NanoDBPedia R100
      type: NanoDBPedia_R100
    metrics:
    - type: map
      value: 0.679
      name: Map
    - type: mrr@10
      value: 0.8939
      name: Mrr@10
    - type: ndcg@10
      value: 0.7494
      name: Ndcg@10
  - task:
      type: cross-encoder-reranking
      name: Cross Encoder Reranking
    dataset:
      name: NanoClimateFEVER R100
      type: NanoClimateFEVER_R100
    metrics:
    - type: map
      value: 0.4903
      name: Map
    - type: mrr@10
      value: 0.7496
      name: Mrr@10
    - type: ndcg@10
      value: 0.5722
      name: Ndcg@10
  - task:
      type: cross-encoder-reranking
      name: Cross Encoder Reranking
    dataset:
      name: NanoSCIDOCS R100
      type: NanoSCIDOCS_R100
    metrics:
    - type: map
      value: 0.3227
      name: Map
    - type: mrr@10
      value: 0.5548
      name: Mrr@10
    - type: ndcg@10
      value: 0.3742
      name: Ndcg@10
  - task:
      type: cross-encoder-reranking
      name: Cross Encoder Reranking
    dataset:
      name: NanoQuoraRetrieval R100
      type: NanoQuoraRetrieval_R100
    metrics:
    - type: map
      value: 0.9608
      name: Map
    - type: mrr@10
      value: 0.98
      name: Mrr@10
    - type: ndcg@10
      value: 0.9753
      name: Ndcg@10
  - task:
      type: cross-encoder-nano-beir
      name: Cross Encoder Nano BEIR
    dataset:
      name: NanoBEIR R100 mean
      type: NanoBEIR_R100_mean
    metrics:
    - type: map
      value: 0.6534
      name: Map
    - type: mrr@10
      value: 0.7695
      name: Mrr@10
    - type: ndcg@10
      value: 0.7063
      name: Ndcg@10
---

# ecbercnl/ettin-reranker-150m-v1-Q8_0-GGUF
This model was converted to GGUF format from [`cross-encoder/ettin-reranker-150m-v1`](https://huggingface.co/cross-encoder/ettin-reranker-150m-v1) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/cross-encoder/ettin-reranker-150m-v1) for more details on the model.

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

```bash
brew install llama.cpp

```
Invoke the llama.cpp server or the CLI.

### CLI:
```bash
llama-cli --hf-repo ecbercnl/ettin-reranker-150m-v1-Q8_0-GGUF --hf-file ettin-reranker-150m-v1-q8_0.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo ecbercnl/ettin-reranker-150m-v1-Q8_0-GGUF --hf-file ettin-reranker-150m-v1-q8_0.gguf -c 2048
```

Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) 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 ecbercnl/ettin-reranker-150m-v1-Q8_0-GGUF --hf-file ettin-reranker-150m-v1-q8_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo ecbercnl/ettin-reranker-150m-v1-Q8_0-GGUF --hf-file ettin-reranker-150m-v1-q8_0.gguf -c 2048
```