keural-dpo2-6500

Keural-DPO2-14.83B (DPO Round 2 — 6,500 steps)

Keural is a bilingual Korean–English Mixture-of-Experts language model trained entirely from scratch by MKD Corp AI Research, Republic of Korea. This is a DPO Round 2 intermediate checkpoint at step 6,500 out of 7,590 total steps (85.6% complete), trained on 485,793 preference pairs.

Model Details

Full Training Pipeline

DPO Round 2 Dataset (485,793 pairs)

Special Tokens

Critical: Always use eos_token_id=131073. The model outputs <|im_end|> (ID 131073) to stop — not <eos> (ID 2).

Chat Format (ChatML)

<|im_start|>system
You are a helpful, accurate, and safe bilingual Korean-English AI assistant. Give concise, factual, and correct answers. If you are not sure about something, say you don't know instead of guessing. Never provide harmful, dangerous, illegal, or false information.<|im_end|>
<|im_start|>user
Your question here<|im_end|>
<|im_start|>assistant

Usage (Transformers)

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "mkd-hossain/keural-dpo2-6500"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)

messages = [
    {"role": "system", "content": "You are a helpful bilingual Korean-English AI assistant."},
    {"role": "user",   "content": "안녕하세요! 서울에 대해 알려주세요."}
]

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,
    temperature=0.7,
    top_p=0.9,
    top_k=50,
    repetition_penalty=1.1,
    do_sample=True,
    eos_token_id=131073,
)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Usage (vLLM)

python -m vllm.entrypoints.openai.api_server \
    --model mkd-hossain/keural-dpo2-6500 \
    --dtype auto \
    --max-model-len 4096 \
    --gpu-memory-utilization 0.7 \
    --trust-remote-code

Hardware

Trained on 2× NVIDIA H200 SXM (139 GiB each) using FSDP FULL_SHARD, bfloat16 mixed precision, and gradient checkpointing.

Organization

Developed by MKD Corp AI Research, Republic of Korea.