Instructions to use skt/A.X-K2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use skt/A.X-K2 with Transformers:

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

pipe = pipeline("text-generation", model="skt/A.X-K2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("skt/A.X-K2")
model = AutoModelForCausalLM.from_pretrained("skt/A.X-K2", device_map="auto")
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 skt/A.X-K2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "skt/A.X-K2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "skt/A.X-K2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/skt/A.X-K2

SGLang

How to use skt/A.X-K2 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 "skt/A.X-K2" \
    --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": "skt/A.X-K2",
		"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 "skt/A.X-K2" \
        --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": "skt/A.X-K2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use skt/A.X-K2 with Docker Model Runner:
```
docker model run hf.co/skt/A.X-K2
```

Where is A.X-K2-Light

by aquilesfd - opened 1 day ago

Discussion

aquilesfd

1 day ago

the 20B MoE size is quite scarce on model options these days. the most recent releases i can think of are Gemma 4 26B, Maple Preview, LFM2 24B and gpt-oss 20b. they'd run pretty well on setups with 6-8GB VRAM, and there is a Light version

"Built on SK Telecom's A.X K2 Light 20B-A3B mixture-of-experts text backbone"

https://huggingface.co/KRAFTON/A.X-K2-Raon-Speech-21B-A3B

singleheart

SK Telecom org about 23 hours ago

Hello @aquilesfd , thank you for the question and for following our releases closely.

A.X K2 Light was developed primarily for internal use and partner integrations, and unfortunately there are no plans to open-source it at this time. We apologize for any disappointment this may cause.

That said, feedback like yours on the demand for smaller MoE models is really valuable to us, and we'll keep it in mind for our future roadmap. We hope you'll continue to enjoy A.X-K2 in the meantime.

singleheart changed discussion status to closed about 23 hours ago

aquilesfd

about 13 hours ago

thank you! love the work you guys have been doing either way

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment