Instructions to use FilippoBetello/RankMistral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FilippoBetello/RankMistral with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="FilippoBetello/RankMistral")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FilippoBetello/RankMistral")
model = AutoModelForCausalLM.from_pretrained("FilippoBetello/RankMistral")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FilippoBetello/RankMistral with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FilippoBetello/RankMistral"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FilippoBetello/RankMistral",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FilippoBetello/RankMistral

SGLang

How to use FilippoBetello/RankMistral with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "FilippoBetello/RankMistral" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FilippoBetello/RankMistral",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "FilippoBetello/RankMistral" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FilippoBetello/RankMistral",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FilippoBetello/RankMistral with Docker Model Runner:
```
docker model run hf.co/FilippoBetello/RankMistral
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for RankMistral

RankMistral, finetuned from Mistral-7B-v0.3 using rank_llm dataset.

Results

From QPP-RA: Aggregating Large Language Model Rankings Using the Rank LLM Library.

Citation

If you use this model please cite:

@inproceedings{10.1145/3731120.3744575,
author = {Betello, Filippo and Russo, Matteo and D\"{u}tting, Paul and Leonardi, Stefano and Silvestri, Fabrizio},
title = {QPP-RA: Aggregating Large Language Model Rankings},
year = {2025},
isbn = {9798400718618},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3731120.3744575},
doi = {10.1145/3731120.3744575},
booktitle = {Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)},
pages = {103–114},
numpages = {12},
keywords = {llm, query performance prediction, rank aggregation},
location = {Padua, Italy},
series = {ICTIR '25}
}

Downloads last month: 1

Safetensors

Model size

7B params

Tensor type

F32

Model tree for FilippoBetello/RankMistral

Quantizations

2 models