Instructions to use lianghsun/Llama-3.2-3B-F1-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lianghsun/Llama-3.2-3B-F1-Base with Transformers:

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

pipe = pipeline("text-generation", model="lianghsun/Llama-3.2-3B-F1-Base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lianghsun/Llama-3.2-3B-F1-Base")
model = AutoModelForCausalLM.from_pretrained("lianghsun/Llama-3.2-3B-F1-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/Llama-3.2-3B-F1-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lianghsun/Llama-3.2-3B-F1-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/Llama-3.2-3B-F1-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lianghsun/Llama-3.2-3B-F1-Base

SGLang

How to use lianghsun/Llama-3.2-3B-F1-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/Llama-3.2-3B-F1-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/Llama-3.2-3B-F1-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/Llama-3.2-3B-F1-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/Llama-3.2-3B-F1-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lianghsun/Llama-3.2-3B-F1-Base with Docker Model Runner:
```
docker model run hf.co/lianghsun/Llama-3.2-3B-F1-Base
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

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 Llama-3.2-3B-F1-Base

Llama-3.2-3B-F1-Base 是 Formosa-1（F1） 系列的 3B 基底模型，以 meta-llama/Llama-3.2-3B 為基底，針對繁體中文與中華民國台灣語境完成持續預訓練（CPT），作為 Llama-3.2-3B-F1-Instruct、Llama-3.2-3B-F1-Reasoning-Instruct 之繁中底座。

⚠️ 規格重點：本模型為 3B 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

Formosa-1 系列在繁中開源社群獲得迴響後，3B 級的 F1 變體在端側部署、研究迭代上有獨特優勢。本模型把 F1 系列的繁中語料注入 Llama-3.2-3B 之參數，作為下游一般指令版（Instruct）與推理版（Reasoning-Instruct）之共同底座。

核心特點 (Key Features)

3B 級繁中底座：兼顧能力與部署成本。
F1 系列家族：作為 Instruct、Reasoning-Instruct 共同基底，下游可在風格與功能上分化。
可端側部署：適合在消費級 GPU、邊緣裝置運行。

Model Description

Developed by: Liang Hsun Huang
Funded by: APMIC
Base model: meta-llama/Llama-3.2-3B
Model type: LlamaForCausalLM (Transformers)
Language(s) (NLP): Traditional Chinese, English
License: MIT

Model Sources

Repository: lianghsun/Llama-3.2-3B-F1-Base

Citation

@misc{llama_3_2_3b_f1_base,
  title        = {Llama-3.2-3B-F1-Base: A Traditional Chinese Continued-Pretrained Llama-3.2 3B Model (Formosa-1 series)},
  author       = {Huang, Liang Hsun},
  year         = {2025},
  howpublished = {\url{https://huggingface.co/lianghsun/Llama-3.2-3B-F1-Base}}
}