Instructions to use CYFRAGOVPL/PLLuM-12b-nc-base-2507 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CYFRAGOVPL/PLLuM-12b-nc-base-2507 with Transformers:

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

pipe = pipeline("text-generation", model="CYFRAGOVPL/PLLuM-12b-nc-base-2507")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CYFRAGOVPL/PLLuM-12b-nc-base-2507")
model = AutoModelForCausalLM.from_pretrained("CYFRAGOVPL/PLLuM-12b-nc-base-2507")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CYFRAGOVPL/PLLuM-12b-nc-base-2507 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CYFRAGOVPL/PLLuM-12b-nc-base-2507"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CYFRAGOVPL/PLLuM-12b-nc-base-2507",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CYFRAGOVPL/PLLuM-12b-nc-base-2507

SGLang

How to use CYFRAGOVPL/PLLuM-12b-nc-base-2507 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 "CYFRAGOVPL/PLLuM-12b-nc-base-2507" \
    --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": "CYFRAGOVPL/PLLuM-12b-nc-base-2507",
		"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 "CYFRAGOVPL/PLLuM-12b-nc-base-2507" \
        --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": "CYFRAGOVPL/PLLuM-12b-nc-base-2507",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CYFRAGOVPL/PLLuM-12b-nc-base-2507 with Docker Model Runner:
```
docker model run hf.co/CYFRAGOVPL/PLLuM-12b-nc-base-2507
```

Can PLLum be converted into ONNX format and used as embedding model?

by batonoff - opened Aug 2, 2025

Discussion

batonoff

Aug 2, 2025

Hello!

I want to load embedding model into Oracle 23ai database. Model will be used to generate embeddings to use with vector search feature. The model must be in ONNX format and meet number of requirements. Can PLLuM be converted into such a model?

Regards,
Marcin.

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