Instructions to use mkd-ai/Keural-Nova-v1.2-experimental with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mkd-ai/Keural-Nova-v1.2-experimental with Transformers:

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

pipe = pipeline("text-generation", model="mkd-ai/Keural-Nova-v1.2-experimental")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("mkd-ai/Keural-Nova-v1.2-experimental")
model = AutoModelForMultimodalLM.from_pretrained("mkd-ai/Keural-Nova-v1.2-experimental", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mkd-ai/Keural-Nova-v1.2-experimental with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mkd-ai/Keural-Nova-v1.2-experimental"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mkd-ai/Keural-Nova-v1.2-experimental",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mkd-ai/Keural-Nova-v1.2-experimental

SGLang

How to use mkd-ai/Keural-Nova-v1.2-experimental 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 "mkd-ai/Keural-Nova-v1.2-experimental" \
    --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": "mkd-ai/Keural-Nova-v1.2-experimental",
		"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 "mkd-ai/Keural-Nova-v1.2-experimental" \
        --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": "mkd-ai/Keural-Nova-v1.2-experimental",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mkd-ai/Keural-Nova-v1.2-experimental with Docker Model Runner:
```
docker model run hf.co/mkd-ai/Keural-Nova-v1.2-experimental
```

Keural Nova v1.2 (experimental)

Keural Nova v1.2 is a bilingual (Korean/English) large language model developed by MKD — an AI company based in Busan, South Korea. It is a LoRA supervised fine-tune of Qwen3.6-35B-A3B (35B parameters, ~3B active MoE), tuned to improve Korean fluency, tool-calling (including long context), and code while preserving the base model's general capability.

⚠️ Experimental release. This is a v1.2 experimental run. It is the strongest Keural Nova to date on code and tool-calling, with honest trade-offs documented below.

Highlights

🥇 Best-in-line tool-calling — 12/12 on our function-calling suite (base Qwen: 11/12), robust multi-turn (call → result → answer), and verified tool-calling in very long context (~237k tokens).
🥇 Code recovered and beats base — HumanEval 68.3 (base 62.2; earlier v1.0/v1.1 had regressed to ~12–21 due to a data issue, now fixed with indentation-validated code).
🥇 Best Korean of the Nova line — KoBEST 70.0 and KMMLU 63.5, the highest of all Keural Nova versions.
🌏 256K native context (Qwen3.6 architecture; up to 1M via YaRN — see Serving).

Evaluation

Same harness (lm-eval, vLLM backend, seed 42) across base and every Keural Nova version.

Benchmark	Base	Nova v1.0	Nova v1.1	Nova v1.2
KoBEST (ko, conversational)	62.88	68.82	67.29	70.03
KMMLU (ko, knowledge)	64.46	62.52	62.38	63.50
HAE-RAE (ko, knowledge)	75.53	73.42	74.52	73.88
MMLU (en, knowledge)	83.83	82.07	82.37	82.88
GSM8K (math, strict)	32.15¹	87.11	86.88	72.25
HumanEval (code)	62.20	20.73	11.59	68.29

¹ Base GSM8K is depressed by answer-format mismatch under strict-match; the fine-tuned gain is largely format compliance.

Tool-calling (our XML function-calling suite, non-thinking, temperature 0):

Metric	Base Qwen	Nova v1.2
Single-turn (12 cases)	11/12	12/12
Multi-turn (call → tool result → final answer)	✅	✅
Long-context tool call (~237k-token context)	—	✅ (correct call + argument)

How v1.2 compares

Better than v1.0 and v1.1 overall — best Korean MCQ (KMMLU), best KoBEST, best MMLU of the fine-tunes, dramatically better code, and the strongest tool-calling (incl. long context).
Trade-offs (honest): GSM8K (72.3) is lower than v1.0/v1.1 (~87) though still far above base; HAE-RAE (73.9) is ~flat vs v1.1 (74.5). Small knowledge dips vs base on MMLU (−0.9) and HAE-RAE (−1.7) are the expected SFT trade-off (SFT tunes style/skill, not stored knowledge).

Intended use

General assistant, Korean/English chat and RAG, agentic / tool-calling workloads (web search, document QA, function calling), and coding. Especially suited to Korean enterprise assistants and agent frameworks.

Serving (vLLM)

Recommended config for the tool/agent workload — native 256K context:

python -m vllm.entrypoints.openai.api_server \
  --model mkd-hossain/Keural-Nova-v1.2-experimental \
  --served-model-name Keural-Nova-v1.2 \
  --tensor-parallel-size 2 --disable-custom-all-reduce \
  --max-model-len 262144 \
  --tool-call-parser qwen3_xml --enable-auto-tool-choice

Non-thinking is the default (the chat template is set so the model answers/tool-calls directly). enable_thinking=true remains available per request.
Tool calls use Qwen XML (<tool_call><function=NAME><parameter=P>VAL</parameter></function></tool_call>) — serve with --tool-call-parser qwen3_xml --enable-auto-tool-choice.
1M context is available via YaRN (rope_scaling, factor 4.0), but static YaRN degrades short-prompt tool-calling on Qwen models generally; serve native 256K for agent/tool use and enable YaRN only when a request truly needs >256K.

Training

Base: Qwen/Qwen3.6-35B-A3B (fine-tuned fresh from base, not from v1.0/v1.1).
Method: LoRA (rank 16, α 32, dropout 0.0) via ms-swift, targeting attention + Gated-DeltaNet linear-attention + shared experts + all routed MoE experts (PEFT target_parameters); router and gates frozen. 1 epoch, LR 5e-5, bf16, DeepSpeed ZeRO-2, 2× H200.
Data: ~~162k examples — a cleaned, balanced Korean/English/code/replay mix (AST-validated code, benchmark test-splits excluded, identity de-contaminated) plus a tool-calling slice (~~17k: single-turn, multi-turn, negative, and long-context up to 32k; sources: Glaive-function-calling-v2 and Hermes-function-calling, both Apache-2.0, converted to Qwen XML) and a small Korean tool-use set.
Design goal: improve Korean + tool-calling + code while holding general capability flat (verified against a base-model eval gate before release).

Limitations

Experimental: intended for evaluation; validate on your workload before production.
GSM8K math word-problems are weaker than Nova v1.0/v1.1.
Small knowledge dips vs base on MMLU / HAE-RAE (expected SFT trade-off).
Tool-calling at the full 1M-YaRN context is not guaranteed (a serving-side YaRN property, not a model defect); native 256K is recommended for agents.
Identity is a fine-tuned behavior; it is not adversarially hardened.

License & attribution

Released under Apache-2.0, inheriting the license of the base model Qwen/Qwen3.6-35B-A3B (© Alibaba Cloud / the Qwen team), whose license and attribution are retained. "Keural" and "Keural Nova" are model names by MKD.

Citation

@misc{keural-nova-v1_2,
  title  = {Keural Nova v1.2 (experimental)},
  author = {MKD},
  year   = {2026},
  url    = {https://huggingface.co/mkd-hossain/Keural-Nova-v1.2-experimental}
}

Downloads last month: 69

Safetensors

Model size

35B params

Tensor type

BF16

Model tree for mkd-ai/Keural-Nova-v1.2-experimental

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

(198)

this model