Instructions to use mkd-hossain/Keural-Cortex-8B-step10000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mkd-hossain/Keural-Cortex-8B-step10000 with Transformers:

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

pipe = pipeline("text-generation", model="mkd-hossain/Keural-Cortex-8B-step10000")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mkd-hossain/Keural-Cortex-8B-step10000")
model = AutoModelForCausalLM.from_pretrained("mkd-hossain/Keural-Cortex-8B-step10000", 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 mkd-hossain/Keural-Cortex-8B-step10000 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mkd-hossain/Keural-Cortex-8B-step10000"
# 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-hossain/Keural-Cortex-8B-step10000",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mkd-hossain/Keural-Cortex-8B-step10000

SGLang

How to use mkd-hossain/Keural-Cortex-8B-step10000 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-hossain/Keural-Cortex-8B-step10000" \
    --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-hossain/Keural-Cortex-8B-step10000",
		"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-hossain/Keural-Cortex-8B-step10000" \
        --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-hossain/Keural-Cortex-8B-step10000",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mkd-hossain/Keural-Cortex-8B-step10000 with Docker Model Runner:
```
docker model run hf.co/mkd-hossain/Keural-Cortex-8B-step10000
```

Keural Cortex 8B — intermediate checkpoint (step 10,000)

An intermediate checkpoint published for research and reproducibility, not for use. For the completed model see Keural-Cortex-8B-Base.

Korean-focused continued pretraining (CPT) of Qwen/Qwen3-8B-Base, by MKD Co., Ltd.


Progress	step 10,000 / 13,034 (76.7%)
Tokens seen	31,457,280,000 (31.46 B) of 41.00 B
LR at this step	1.0e-05 (WSD stable phase)
Context length	32,768 (native)
Exported	2026-09-05

Why this checkpoint is published

Training loss in this run plateaued at ≈1.818 from roughly step 5,200 (16.4 B tokens) and did not improve materially through to step 13,034 — the WSD decay phase contributed +0.0007. Whether downstream capability continued improving after that plateau is an open question, and answering it requires comparing checkpoints from across the run.

This checkpoint exists so that comparison is possible. Alongside step5000 (15.73 B tokens, 38%) and the final model (41.00 B, 100%), it gives three points spanning the plateau — one before it, two after — on an otherwise identical run.

⚠️ Limitations

Base model. No instruction following, no chat format, no tool calling, no thinking mode. It continues text rather than answering instructions. Post-training has not been performed. The bundled chat_template.jinja is inherited from the base tokenizer and does not indicate chat tuning.
Not evaluated. No benchmark numbers exist for this checkpoint.
Decontamination outstanding. N-gram overlap against the evaluation suites has not been checked.
Mid-training. The learning rate had not yet decayed at this point, so this is not a "finished" model in any sense — the final checkpoint saw a full decay to 1.0e-06.

Training configuration

Identical to the final checkpoint: sequence length 4,096, global batch 3,145,728 tokens/step, peak LR 1.0e-05 on a WSD schedule, AdamW (β 0.9/0.95, wd 0.1), grad clip 1.0, FSDP full shard on 4 × H200, bf16 with fp32 gradient reduction, FlashAttention-2, activation checkpointing.

Corpus: 38.784 B tokens across 19 sources — 42.45% Korean, 29.71% English/other, 15.19% code, 12.66% science/math. NamuWiki, Falcon-RefinedWeb and arXiv were excluded on licensing grounds.

Full details, including the loss analysis referenced above: github.com/MKD-CORP/Keural-Cortex-8B under CPT_details/.

License

Apache 2.0, inherited from Qwen/Qwen3-8B-Base. Derivative work of Qwen3-8B-Base by Alibaba Cloud; attribution required.

Intended use

Research and checkpoint comparison only. Not for production or user-facing deployment.

Downloads last month: 150

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for mkd-hossain/Keural-Cortex-8B-step10000

Base model

Qwen/Qwen3-8B-Base

Finetuned

(563)

this model