Instructions to use reglab-rrc/mistral-rrc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use reglab-rrc/mistral-rrc with Transformers:

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

pipe = pipeline("text-generation", model="reglab-rrc/mistral-rrc")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("reglab-rrc/mistral-rrc")
model = AutoModelForMultimodalLM.from_pretrained("reglab-rrc/mistral-rrc")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use reglab-rrc/mistral-rrc with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/reglab-rrc/mistral-rrc

SGLang

How to use reglab-rrc/mistral-rrc 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 "reglab-rrc/mistral-rrc" \
    --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": "reglab-rrc/mistral-rrc",
		"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 "reglab-rrc/mistral-rrc" \
        --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": "reglab-rrc/mistral-rrc",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use reglab-rrc/mistral-rrc with Docker Model Runner:
```
docker model run hf.co/reglab-rrc/mistral-rrc
```

Fixed quotation not working

by gtvracer - opened Apr 10, 2025

Discussion

gtvracer

Apr 10, 2025

Hello,
Thank you for your work! I just got it working and ran a sample deed. It did find the text with racial covenant, returned the raw passage, but the quotation is still the same as the raw passage, fyi. I basically copied the steps on the model card, so I don't think I'm missing anything. Perhaps something was left out of the directions?
Thanks again!

Have Racial Covenant: Yes
Raw Passage: that in so far as said property may be used for residence purposes it shall never be occupied by any person not of the Caucasian race.
Quotation: that in so far as said property may be used for residence purposes it shall never be occupied by any person not of the Caucasian race.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment