Instructions to use llaa33219/Vere1Ko-360M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llaa33219/Vere1Ko-360M with Transformers:

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

pipe = pipeline("text-generation", model="llaa33219/Vere1Ko-360M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("llaa33219/Vere1Ko-360M")
model = AutoModelForCausalLM.from_pretrained("llaa33219/Vere1Ko-360M")
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 Settings

vLLM

How to use llaa33219/Vere1Ko-360M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llaa33219/Vere1Ko-360M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llaa33219/Vere1Ko-360M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/llaa33219/Vere1Ko-360M

SGLang

How to use llaa33219/Vere1Ko-360M 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 "llaa33219/Vere1Ko-360M" \
    --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": "llaa33219/Vere1Ko-360M",
		"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 "llaa33219/Vere1Ko-360M" \
        --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": "llaa33219/Vere1Ko-360M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use llaa33219/Vere1Ko-360M with Docker Model Runner:
```
docker model run hf.co/llaa33219/Vere1Ko-360M
```

1. Vere Series

The Vere series has the following characteristics:

Small Size: The model itself is small, allowing it to run in various environments.
Focus on a Single Field: As a small model, it is difficult to excel in all areas. Therefore, it is trained to specialize in a specific field rather than being a generalist.
Variety of Models: Since it doesn't cover all fields, many specialized models are released for each area (with more diverse models planned for the future).

2. VereKo Series

VereKo has the following characteristics:

Korean Specialization: It has been trained on a large amount of Korean data, making it proficient in the Korean language.

3. About This Model

Model Name: Vere1Ko-360M
Base Model: HuggingFaceTB/SmolLM2-360M-Instruct
Fine-tuning Dataset: MarkrAI/KoCommercial-Dataset
Small Size: Can be executed on low-performance devices with 360M parameters
Korean Language Specialized: Fine-tuned with Korean language datasets and specialized for Korean