Qwen3-30B-A3B-Kaidol-v4

Korean character roleplay model fine-tuned from Qwen3-30B-A3B-Instruct-2507.

Model Description

This model is optimized for Korean character roleplay conversations, trained with custom character datasets featuring distinct personalities, speech patterns, and emotional expressions.

Training Details

Parameter	Value
Base Model	Qwen/Qwen3-30B-A3B-Instruct-2507
Method	LoRA (merged)
LoRA Rank	32
LoRA Alpha	64
Target Modules	q_proj, k_proj, v_proj, o_proj
Training Epochs	3
Learning Rate	2e-5
Max Sequence Length	2048

Target Modules

• Attention only: q_proj, k_proj, v_proj, o_proj

Intended Use

This model is designed for:

• Korean character roleplay conversations
• Interactive storytelling
• Character-based chat applications

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "developer-lunark/Qwen3-30B-A3B-Kaidol-v4"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "안녕하세요!"}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

vLLM Serving

vllm serve developer-lunark/Qwen3-30B-A3B-Kaidol-v4 \
    --tensor-parallel-size 2 \
    --max-model-len 8192

Limitations

• Optimized for Korean language; performance in other languages may vary
• Character roleplay focused; may not be optimal for factual Q&A
• Inherits limitations from the base Qwen3 model

License

Apache 2.0 (following the base model license)

Acknowledgments

• Base model: Qwen/Qwen3-30B-A3B-Instruct-2507
• Fine-tuned by developer-lunark