Instructions to use lianghsun/F1-24B-Instruct-Cybersecurity with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lianghsun/F1-24B-Instruct-Cybersecurity with Transformers:

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

pipe = pipeline("text-generation", model="lianghsun/F1-24B-Instruct-Cybersecurity")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lianghsun/F1-24B-Instruct-Cybersecurity")
model = AutoModelForCausalLM.from_pretrained("lianghsun/F1-24B-Instruct-Cybersecurity")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use lianghsun/F1-24B-Instruct-Cybersecurity with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lianghsun/F1-24B-Instruct-Cybersecurity"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lianghsun/F1-24B-Instruct-Cybersecurity",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lianghsun/F1-24B-Instruct-Cybersecurity

SGLang

How to use lianghsun/F1-24B-Instruct-Cybersecurity 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 "lianghsun/F1-24B-Instruct-Cybersecurity" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lianghsun/F1-24B-Instruct-Cybersecurity",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "lianghsun/F1-24B-Instruct-Cybersecurity" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lianghsun/F1-24B-Instruct-Cybersecurity",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lianghsun/F1-24B-Instruct-Cybersecurity with Docker Model Runner:
```
docker model run hf.co/lianghsun/F1-24B-Instruct-Cybersecurity
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Model Card for F1-24B-Instruct-Cybersecurity

F1-24B-Instruct-Cybersecurity 是 Formosa-1（F1） 系列在資通安全（cybersecurity）領域的專業微調模型，建構於 F1-24B-Base 之上，以資安相關之繁中對話資料完成 SFT，提供台灣資安實務語境下的繁中專業對話能力。

⚠️ 規格重點：本模型為 24B 參數領域微調模型、純文本單模態，僅供研究與實務輔助，不應作為事故應變或法遵之單一決策依據。

Model Details

資安事件與法遵情境（如《資通安全管理法》及其子法）具高度在地化特性，通用模型常無法準確回答。本模型在 F1-24B-Base 之繁中底座上，以資安術語、漏洞通報、事件應變、法遵程序等為訓練主題，使其在台灣資安實務情境下能提供可用的回應。

核心特點 (Key Features)

資安領域專精：訓練資料針對台灣資安實務（術語、法規、流程）。
24B 級可部署：能力與成本兼顧，適合企業／公部門資安團隊內部部署。
F1 家族成員：可與 F1-24B-Instruct、F1-24B-Reasoner 互補使用。

Model Description

Developed by: Liang Hsun Huang
Funded by: APMIC
Base model: lianghsun/F1-24B-Base
Model type: MistralForCausalLM (Transformers)
Language(s) (NLP): Traditional Chinese, English
License: MIT
Finetuned from model: lianghsun/F1-24B-Base

Model Sources

Repository: lianghsun/F1-24B-Instruct-Cybersecurity

Citation

@misc{f1_24b_instruct_cybersecurity,
  title        = {F1-24B-Instruct-Cybersecurity: A Cybersecurity Domain-specific Traditional Chinese Model for Taiwan},
  author       = {Huang, Liang Hsun},
  year         = {2025},
  howpublished = {\url{https://huggingface.co/lianghsun/F1-24B-Instruct-Cybersecurity}}
}