Instructions to use youngseok12/AX-3.1-Light-sft_v3_1_A_control with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use youngseok12/AX-3.1-Light-sft_v3_1_A_control with Transformers:

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

pipe = pipeline("text-generation", model="youngseok12/AX-3.1-Light-sft_v3_1_A_control")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("youngseok12/AX-3.1-Light-sft_v3_1_A_control")
model = AutoModelForCausalLM.from_pretrained("youngseok12/AX-3.1-Light-sft_v3_1_A_control", 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 youngseok12/AX-3.1-Light-sft_v3_1_A_control with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "youngseok12/AX-3.1-Light-sft_v3_1_A_control"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "youngseok12/AX-3.1-Light-sft_v3_1_A_control",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/youngseok12/AX-3.1-Light-sft_v3_1_A_control

SGLang

How to use youngseok12/AX-3.1-Light-sft_v3_1_A_control 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 "youngseok12/AX-3.1-Light-sft_v3_1_A_control" \
    --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": "youngseok12/AX-3.1-Light-sft_v3_1_A_control",
		"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 "youngseok12/AX-3.1-Light-sft_v3_1_A_control" \
        --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": "youngseok12/AX-3.1-Light-sft_v3_1_A_control",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use youngseok12/AX-3.1-Light-sft_v3_1_A_control with Docker Model Runner:
```
docker model run hf.co/youngseok12/AX-3.1-Light-sft_v3_1_A_control
```

AX-3.1-Light-sft_v3_1_A_control

This is a standalone BF16 model obtained by fine-tuning skt/A.X-3.1-Light with a LoRA adapter and merging the adapter into the base weights. It is intended for Korean-language research and controlled evaluation. The repository contains no benchmark data, benchmark answers, training logs, or access credentials.

Model Details

Base model: skt/A.X-3.1-Light
Base revision used for training and merge: 9b41bb2406472634d8812c0b8931fa40fa9a6c3a
Architecture: unchanged from the base model
Weight format: BF16 safetensors
Chat template: official A.X tokenizer chat template
Custom Python model code: none
Submission form: merged full model; no separate adapter is required
Experiment condition: Control run for measuring the effect of the alternative v3.1 mixtures.

Training Data

The training split contains 36,000 examples and the AI Hub validation-derived development split contains 3,000 examples. Source-level train/dev separation and exact-duplicate checks were retained. The source domains were:

Civil law LLM instruction-tuning data
Criminal law LLM instruction-tuning data
Administrative law LLM instruction-tuning data
Corporate accounting standards data
Essential medical knowledge data
News article machine-reading data
CoT-Fabric technology valuation data

The v3.0 clean 36,000-example mixture was retained as the control condition. 55.80% of assistant target tokens (3,000 reasoning examples).

Public evaluation benchmarks such as KMMLU-Pro, CLIcK, HLE, SNU Ko-MuSR, Com2-main, and Original MuSR were not used as SFT data.

Training Procedure

Objective: standard assistant-token causal-language-model cross entropy
Epochs: 1
Learning rate: 3e-5
Scheduler: cosine with 0.03 warmup ratio
Weight decay: 0.01
Maximum gradient norm: 1.0
LoRA: rank 16, alpha 32, dropout 0.05
LoRA target modules: q_proj, k_proj, v_proj, o_proj
Effective batch size: 32
Maximum sequence length: 2048
Precision: BF16
Packing: disabled
Random seed: 20260827

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "youngseok12/AX-3.1-Light-sft_v3_1_A_control"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id, dtype=torch.bfloat16, device_map="auto"
)
messages = [{"role": "user", "content": "대한민국의 수도는 어디인가요?"}]
inputs = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=True, return_tensors="pt"
).to(model.device)
with torch.inference_mode():
    outputs = model.generate(**inputs, max_new_tokens=64, do_sample=False)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))

For an OpenAI-compatible deployment, the merged repository is intended to be loadable directly by standard vLLM without an adapter or trust_remote_code. Run the K-AI submission compatibility checks separately before submission.

Intended Use and Limitations

This model is an experimental Korean SFT model for research and controlled evaluation. It can produce factual errors and should not be used as a substitute for professional legal, accounting, medical, or financial advice. The AI Hub source data remains subject to its original access terms.

License

The base model is distributed under the Apache License 2.0. The applicable terms of the AI Hub source data remain in force for use of the training data. See LICENSE for the base model license text.

Downloads last month: 427

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for youngseok12/AX-3.1-Light-sft_v3_1_A_control

Base model

skt/A.X-3.1-Light

Finetuned

(22)

this model