Instructions to use flowos/teeem-pii-ko-1.2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flowos/teeem-pii-ko-1.2b with Transformers:

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

pipe = pipeline("text-generation", model="flowos/teeem-pii-ko-1.2b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("flowos/teeem-pii-ko-1.2b")
model = AutoModelForCausalLM.from_pretrained("flowos/teeem-pii-ko-1.2b")
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 flowos/teeem-pii-ko-1.2b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "flowos/teeem-pii-ko-1.2b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "flowos/teeem-pii-ko-1.2b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/flowos/teeem-pii-ko-1.2b

SGLang

How to use flowos/teeem-pii-ko-1.2b 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 "flowos/teeem-pii-ko-1.2b" \
    --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": "flowos/teeem-pii-ko-1.2b",
		"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 "flowos/teeem-pii-ko-1.2b" \
        --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": "flowos/teeem-pii-ko-1.2b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use flowos/teeem-pii-ko-1.2b with Docker Model Runner:
```
docker model run hf.co/flowos/teeem-pii-ko-1.2b
```

teeem-pii-ko-1.2b / patterns_typescript /name.test.ts

flowos

iter 14: hybrid regex + fine-tuned EXAONE 4.0 1.2B (F1=0.930)

1bcb098 verified about 2 months ago

raw

history blame contribute delete

2.34 kB

	import { describe, it, expect } from "vitest";
	import { detectName } from "./name.js";

	describe("Korean name detection", () => {
	it("detects common Korean names", () => {
	expect(detectName("김철수 님")).toHaveLength(1);
	expect(detectName("이영희 입니다")).toHaveLength(1);
	expect(detectName("박민수")).toHaveLength(1);
	});

	it("detects names with various top surnames", () => {
	expect(detectName("최지원")).toHaveLength(1);
	expect(detectName("정하나")).toHaveLength(1);
	expect(detectName("강민호")).toHaveLength(1);
	});

	it("detects 2-char names (surname + 1 char)", () => {
	expect(detectName("김솔")).toHaveLength(1);
	expect(detectName("이준")).toHaveLength(1);
	});

	it("rejects single character (surname only)", () => {
	// "김" alone is just a surname, not a full name
	expect(detectName("김 입니다")).toHaveLength(0);
	});

	it("detects multiple names in text", () => {
	const r = detectName("김철수와 이영희가 만났다");
	expect(r).toHaveLength(2);
	});

	it("has lower confidence than other PII types", () => {
	const r = detectName("김철수");
	if (r.length > 0) {
	expect(r[0].confidence).toBeLessThan(0.8);
	}
	});

	it("returns empty for non-Korean text", () => {
	expect(detectName("John Smith")).toHaveLength(0);
	expect(detectName("hello world")).toHaveLength(0);
	});

	it("excludes common Korean words that start with surname chars", () => {
	// These words start with top surnames but are not names
	expect(detectName("오늘")).toHaveLength(0);
	expect(detectName("전화")).toHaveLength(0);
	expect(detectName("서버")).toHaveLength(0);
	expect(detectName("주소")).toHaveLength(0);
	expect(detectName("한국")).toHaveLength(0);
	expect(detectName("고객")).toHaveLength(0);
	expect(detectName("최근")).toHaveLength(0);
	expect(detectName("문제")).toHaveLength(0);
	expect(detectName("안내")).toHaveLength(0);
	expect(detectName("신청")).toHaveLength(0);
	});

	it("still detects real names despite exclusion list", () => {
	// These are valid names, not in the exclusion list
	expect(detectName("오세진")).toHaveLength(1);
	expect(detectName("전지현")).toHaveLength(1);
	expect(detectName("서연우")).toHaveLength(1);
	});
	});