Instructions to use CYFRAGOVPL/Llama-PLLuM-8B-base-2508 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CYFRAGOVPL/Llama-PLLuM-8B-base-2508 with Transformers:

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

pipe = pipeline("text-generation", model="CYFRAGOVPL/Llama-PLLuM-8B-base-2508")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CYFRAGOVPL/Llama-PLLuM-8B-base-2508")
model = AutoModelForCausalLM.from_pretrained("CYFRAGOVPL/Llama-PLLuM-8B-base-2508", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CYFRAGOVPL/Llama-PLLuM-8B-base-2508 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CYFRAGOVPL/Llama-PLLuM-8B-base-2508"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CYFRAGOVPL/Llama-PLLuM-8B-base-2508",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CYFRAGOVPL/Llama-PLLuM-8B-base-2508

SGLang

How to use CYFRAGOVPL/Llama-PLLuM-8B-base-2508 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/Llama-PLLuM-8B-base-2508" \
    --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/Llama-PLLuM-8B-base-2508",
		"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/Llama-PLLuM-8B-base-2508" \
        --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/Llama-PLLuM-8B-base-2508",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CYFRAGOVPL/Llama-PLLuM-8B-base-2508 with Docker Model Runner:
```
docker model run hf.co/CYFRAGOVPL/Llama-PLLuM-8B-base-2508
```

Llama-PLLuM-8B-base-2508

Commit History

Update tokenizer_config.json

98f3e24
verified

grajewskad commited on Aug 6

Update README.md

abfb430
verified

grajewskad commited on May 19

Update README.md

b632e26
verified

akarlinska commited on Aug 1, 2025

Update README.md

74d9238
verified

akarlinska commited on Aug 1, 2025

Update README.md

9b2e592
verified

akarlinska commited on Aug 1, 2025

Update README.md

02474f5
verified

akarlinska commited on Aug 1, 2025

Update README.md

e5698da
verified

akarlinska commited on Aug 1, 2025

Added model

5a19426

Bartłomiej Koptyra commited on Aug 1, 2025

initial commit

64ee15a
verified

bkoptyra commited on Aug 1, 2025

Commit History

Update tokenizer_config.json 98f3e24 verified

Update README.md abfb430 verified

Update README.md b632e26 verified

Update README.md 74d9238 verified

Update README.md 9b2e592 verified

Update README.md 02474f5 verified

Update README.md e5698da verified

Added model 5a19426

initial commit 64ee15a verified

Update tokenizer_config.json

98f3e24
verified

Update README.md

abfb430
verified

Update README.md

b632e26
verified

Update README.md

74d9238
verified

Update README.md

9b2e592
verified

Update README.md

02474f5
verified

Update README.md

e5698da
verified

Added model

5a19426

initial commit

64ee15a
verified