Instructions to use lopentu/Taiwan-Lawstral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lopentu/Taiwan-Lawstral with Transformers:

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

pipe = pipeline("text-generation", model="lopentu/Taiwan-Lawstral")

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

tokenizer = AutoTokenizer.from_pretrained("lopentu/Taiwan-Lawstral")
model = AutoModelForCausalLM.from_pretrained("lopentu/Taiwan-Lawstral", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lopentu/Taiwan-Lawstral with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/lopentu/Taiwan-Lawstral

SGLang

How to use lopentu/Taiwan-Lawstral 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 "lopentu/Taiwan-Lawstral" \
    --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": "lopentu/Taiwan-Lawstral",
		"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 "lopentu/Taiwan-Lawstral" \
        --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": "lopentu/Taiwan-Lawstral",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lopentu/Taiwan-Lawstral with Docker Model Runner:
```
docker model run hf.co/lopentu/Taiwan-Lawstral
```

Model Details

Continually pretrained from MediaTek-Research/Breeze-7B-32k-Base-v1_0
Base model with no instruction fine-tuning

Training Details

Hardware: 2 NVIDIA DGX H100 nodes on Taipei-1
Software: NVIDIA NeMo and NVIDIA NeMo Framework Launcher
Training time: 7 days
Context length: 8192 tokens
Steps: 81783
Global batch size: 112
Epochs: 3
Tokens trained on: 75B+
Learning rate:
- Schedule: Cosine
- Warmup steps: 107
- Constant steps: 11873
- Max LR: 1e-4
- Min LR: 1e-5

Dataset Details

Trained mostly on Taiwan legal documents
Tokens: 25B

Downloads last month: 15

Safetensors

Model size

7B params

Tensor type

BF16

Collection including lopentu/Taiwan-Lawstral

Taiwan Legal LLMs

Collection

Models trained from our paper "Continual Pre-Training is (not) What You Need in Domain Adaptation." • 9 items • Updated Nov 8, 2025