Instructions to use youngseok12/HyperCLOVA-X-SEED-Think-14B-sft-71875-3000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use youngseok12/HyperCLOVA-X-SEED-Think-14B-sft-71875-3000 with Transformers:

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

pipe = pipeline("text-generation", model="youngseok12/HyperCLOVA-X-SEED-Think-14B-sft-71875-3000", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("youngseok12/HyperCLOVA-X-SEED-Think-14B-sft-71875-3000", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("youngseok12/HyperCLOVA-X-SEED-Think-14B-sft-71875-3000", trust_remote_code=True, 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 youngseok12/HyperCLOVA-X-SEED-Think-14B-sft-71875-3000 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "youngseok12/HyperCLOVA-X-SEED-Think-14B-sft-71875-3000"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "youngseok12/HyperCLOVA-X-SEED-Think-14B-sft-71875-3000",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/youngseok12/HyperCLOVA-X-SEED-Think-14B-sft-71875-3000

SGLang

How to use youngseok12/HyperCLOVA-X-SEED-Think-14B-sft-71875-3000 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 "youngseok12/HyperCLOVA-X-SEED-Think-14B-sft-71875-3000" \
    --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": "youngseok12/HyperCLOVA-X-SEED-Think-14B-sft-71875-3000",
		"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 "youngseok12/HyperCLOVA-X-SEED-Think-14B-sft-71875-3000" \
        --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": "youngseok12/HyperCLOVA-X-SEED-Think-14B-sft-71875-3000",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use youngseok12/HyperCLOVA-X-SEED-Think-14B-sft-71875-3000 with Docker Model Runner:
```
docker model run hf.co/youngseok12/HyperCLOVA-X-SEED-Think-14B-sft-71875-3000
```

HyperCLOVA X SEED Think-14B — AI Hub 71875 SFT 3K

This repository contains a standalone BF16 model derived from naver-hyperclovax/HyperCLOVAX-SEED-Think-14B. One LoRA adapter was trained on 3,000 examples from AI Hub dataset 71875 and merged into the pristine base weights.

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 from the base
LoRA: rank 16, alpha 32, dropout 0.05, bias none
Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Objective: assistant-token-only causal-language-model cross entropy
Learning rate: 5e-5
Scheduler: cosine, warmup ratio 0.03, weight decay 0
Training: 3,000 examples, 1 epoch, effective batch size 16
Per-device batch: 4; gradient accumulation: 4
Maximum sequence length: 4096; precision: BF16; packing: false
Seed: 42; data seed: 42
Public benchmark data: not used

Training data

The training data is AI Hub 71875 필수의료 의학지식 QA. The exact prepared input contained 3,000 unique rows with the following groups: 내과 865, 산부인과 865, 소아청소년과 865, 응급의학과 405. Targets use an answer-first format containing the correct choice and its text. The source file hash is ff13bf66d46102c773d28934239ec347117726c617df74b6443b0763991cfa60.

Dataset page: https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&aihubDataSe=realm&dataSetSn=71875

No other AI Hub dataset, v0.21 mixture, public benchmark question, benchmark answer, evaluation artifact, log, credential, or .env file is included in this repository. AI Hub source-data terms remain applicable.

Intended use and limitations

This is an experimental Korean-language fine-tuned model for research and controlled evaluation. It can produce factual or reasoning errors and is not a substitute for professional medical, legal, 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 and the AI Hub source-data terms.

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "youngseok12/HyperCLOVA-X-SEED-Think-14B-sft-71875-3000"
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))

Downloads last month: 268

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for youngseok12/HyperCLOVA-X-SEED-Think-14B-sft-71875-3000

Base model

naver-hyperclovax/HyperCLOVAX-SEED-Think-14B

Finetuned

(19)

this model