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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lianghsun/F1-24B-Base")
model = AutoModelForCausalLM.from_pretrained("lianghsun/F1-24B-Base")
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-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lianghsun/F1-24B-Base"
# 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-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use lianghsun/F1-24B-Base 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-Base" \
    --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-Base",
		"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-Base" \
        --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-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

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-Base

F1-24B-Base 是 Formosa-1（F1） 系列中的 24B 基底模型，以 mistralai/Mistral-Small-24B-Base-2501 為基底，針對繁體中文與中華民國台灣語境完成大規模持續預訓練（continued pretraining, CPT），作為 F1-24B-Instruct、F1-24B-Reasoner 等下游模型的繁中底座。

⚠️ 規格重點：本模型為 24B 參數、純文本單模態，僅做 CPT、未做指令微調，需自行 SFT 後才有對話能力。

Model Details

Mistral-Small-24B 是兼顧能力與部署成本的中型開源模型，但其原生繁中與台灣語境覆蓋不足。F1-24B-Base 將 Formosa-1 系列的繁中語料注入 Mistral-Small-24B 之參數，使下游任務能在熟悉繁中與台灣語境之底座上做後續訓練。

核心特點 (Key Features)

24B 級繁中底座：在能力與部署成本之間取得平衡，可作為企業級繁中模型的微調起點。
F1 系列家族基底：作為 Instruct、Reasoner、領域微調（如 F1-24B-Instruct-Cybersecurity）的共同底座。
大規模 CPT：以多卡分散式訓練於繁中語料完成持續預訓練。

Model Description

Developed by: Liang Hsun Huang
Funded by: APMIC
Base model: mistralai/Mistral-Small-24B-Base-2501
Model type: MistralForCausalLM (Transformers)
Language(s) (NLP): Traditional Chinese, English
License: MIT

Model Sources

Repository: lianghsun/F1-24B-Base

Citation

@misc{f1_24b_base,
  title        = {F1-24B-Base: A Traditional Chinese Continued-Pretrained Mistral-24B Model for Taiwan},
  author       = {Huang, Liang Hsun},
  year         = {2025},
  howpublished = {\url{https://huggingface.co/lianghsun/F1-24B-Base}}
}