Instructions to use outprime/gasztold-0.3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use outprime/gasztold-0.3B with Transformers:

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

pipe = pipeline("text-generation", model="outprime/gasztold-0.3B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("outprime/gasztold-0.3B")
model = AutoModelForCausalLM.from_pretrained("outprime/gasztold-0.3B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use outprime/gasztold-0.3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "outprime/gasztold-0.3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "outprime/gasztold-0.3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/outprime/gasztold-0.3B

SGLang

How to use outprime/gasztold-0.3B 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 "outprime/gasztold-0.3B" \
    --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": "outprime/gasztold-0.3B",
		"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 "outprime/gasztold-0.3B" \
        --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": "outprime/gasztold-0.3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use outprime/gasztold-0.3B with Docker Model Runner:
```
docker model run hf.co/outprime/gasztold-0.3B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Gasztold-0.3B

Gasztold-0.3B is a 0.3B-parameter causal language model trained from scratch for Polish legal-language text generation and experimentation.

Model Details

Parameters: 294,908,928
Vocabulary size: 50,000
Type: causal language model
Language: Polish
Domain: Polish legal text
Training: from scratch
Base model: none

Intended Use

The model is intended for research and prototyping in legal NLP, including:

legal text continuation
summarization-style prompting
statutory-language analysis
retrieval-augmented legal assistant experiments

Important Notice

This model is not a lawyer and does not provide legal advice. Outputs may be incomplete, outdated, or incorrect. Any legal interpretation should be verified by a qualified professional.

License

Apache-2.0.

Downloads last month: 43

Safetensors

Model size

0.3B params

Tensor type

F32

Model tree for outprime/gasztold-0.3B

Quantizations

1 model