Instructions to use PleIAs/Pleias-RAG-350M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PleIAs/Pleias-RAG-350M with Transformers:

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

pipe = pipeline("text-generation", model="PleIAs/Pleias-RAG-350M")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PleIAs/Pleias-RAG-350M")
model = AutoModelForCausalLM.from_pretrained("PleIAs/Pleias-RAG-350M", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PleIAs/Pleias-RAG-350M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PleIAs/Pleias-RAG-350M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PleIAs/Pleias-RAG-350M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/PleIAs/Pleias-RAG-350M

SGLang

How to use PleIAs/Pleias-RAG-350M 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 "PleIAs/Pleias-RAG-350M" \
    --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": "PleIAs/Pleias-RAG-350M",
		"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 "PleIAs/Pleias-RAG-350M" \
        --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": "PleIAs/Pleias-RAG-350M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PleIAs/Pleias-RAG-350M with Docker Model Runner:
```
docker model run hf.co/PleIAs/Pleias-RAG-350M
```

Add some metadata to the model card

by tomaarsen HF Staff - opened Apr 24, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-1

tomaarsen

Apr 24, 2025

Hello!

Preface

Nice work here! I'm excited to see models of this size for RAG. I'm going to dive more into your official library next.

Pull Request overview

Add transformers tag
Add text-generation pipeline tag

Details

These should make it a tad easier to find this model.

Also, as a heads up, in my experience, a small snippet in the model card with usage is often recommended to get people a good feel of what your model does, e.g.:

rag = RAGWithCitations("PleIAs/Pleias-RAG-350M")

# Define query and sources
query = "What is the capital of France?"
sources = [
    {
        "text": "Paris is the capital and most populous city of France.",
        "metadata": {"source": "Geographic Encyclopedia", "reliability": "high"}
    },
    {
        "text": "The Eiffel Tower is located in Paris, France.",
        "metadata": {"source": "Travel Guide", "year": 2020}
    }
]

# Generate a response
response = rag.generate(query, sources)

# Print the final answer with citations
print(response["processed"]["clean_answer"])

(Except also include the import & printed output)

Tom Aarsen

Add some metadata to the model card1b3a4e6f

tomaarsen

Apr 24, 2025

Also, am I correct in understanding that this model should be applied after the Retrieval step in the RAG pipeline?

Tom Aarsen

Pclanglais

PleIAs org Apr 24, 2025

Yes exactly on all counts. It's not an embedding model (though a later iteration may come with some search capacities)

Pclanglais changed pull request status to merged Apr 24, 2025

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