youngseok12/HyperCLOVA-X-SEED-Think-14B-minimal-sft-71875

HyperCLOVA X SEED 14B Think — Minimal SFT (AI Hub 71875)

This repository contains a standalone BF16 model derived from `naver-hyperclovax/HyperCLOVAX-SEED-Think-14B`. A deliberately minimal LoRA adapter was trained and merged into the base weights for a first real leaderboard submission probe. The model name begins with HyperCLOVA X as required by the base model license.

Model details

• —Base model: naver-hyperclovax/HyperCLOVAX-SEED-Think-14B
• —Base revision: 9b74e35d4c7e4ffec489f4171273caca8948a2b9
• —Architecture: HyperCLOVAXForCausalLM
• —Weight format: BF16 safetensors, standalone merged full model
• —Chat template: official HyperCLOVA X template, preserved byte-for-byte
• —LoRA: rank 4, alpha 8, dropout 0, target modules q_proj, v_proj
• —Objective: assistant-token causal-language-model cross entropy
• —Learning rate: 1e-6, constant scheduler, no warmup or weight decay
• —Training: 512 examples, 1 epoch, 32 optimizer steps, effective batch 16
• —Maximum sequence length: 1024; precision: BF16; seed: 42
• —Public benchmark data: not used

The run first evaluated 746 eligible private-training candidates and retained 512 rows for which the pristine base model produced an unambiguous correct multiple-choice label. The source was the AI Hub dataset 71875; use of that data remains subject to the source dataset's terms. No benchmark questions, answers, evaluation artifacts, logs, credentials, or .env files are included in this repository.

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "youngseok12/HyperCLOVA-X-SEED-Think-14B-minimal-sft-71875"
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))

Intended use and limitations

This is an experimental Korean-language fine-tuned model for research and controlled evaluation. It may produce factual or reasoning errors and is not a substitute for professional legal, medical, financial, or other advice. The HyperCLOVA X acceptable-use restrictions and all applicable laws continue to apply to this derivative model.

License and notices

The full HyperCLOVA X SEED 14B Think Model License Agreement is included in LICENSE, and the required NAVER attribution is in NOTICE. Redistribution must comply with that agreement, including its prohibited-use policy and attribution requirements. AI Hub source-data terms also remain applicable.