Instructions to use kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF",
	filename="hyper_clova_seed-1.5b-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF with Ollama:
```
ollama run hf.co/kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF to start chatting

Docker Model Runner
How to use kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF with Docker Model Runner:
```
docker model run hf.co/kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF:Q4_K_M
```

Lemonade

How to use kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF-Q4_K_M

List all available models

lemonade list

HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF

1. 개요 (Overview)

본 저장소는 네이버의 한국어 특화 경량 모델인 HyperCLOVA X SEED-Text-Instruct-1.5B를 로컬 환경(LM Studio, Ollama 등)에서 쉽게 사용할 수 있도록 GGUF 형식으로 변환한 파일입니다.

2. 모델 정보 (Model Details)

원본 모델: naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-1.5B
변환 도구: llama.cpp
파일 형식: GGUF (FP16) - 원본의 정밀도를 유지한 버전입니다.

3. 라이선스 (License)

본 모델은 네이버의 HyperCLOVA X SEED 모델 라이선스를 따릅니다.

상업적 이용: 개인 및 기업은 월간 활성 사용자(MAU) 1,000만 명 이하인 경우 무료로 상업적 이용이 가능합니다.
제한 사항: MAU 1,000만 명 초과 시 별도 협의가 필요하며, 네이버와 경쟁 관계에 있는 서비스에는 이용이 제한될 수 있습니다.

4. 실행 방법 (How to use)

llama.cpp 사용 시

  llama-cli -m hyper_clova_seed-1.5b-f16.gguf

5. 제공 파일 정보 (Provided Files)

본 저장소는 사용자의 하드웨어 환경에 맞춰 선택할 수 있는 두 가지 버전을 제공합니다.

파일명	용량	특징	추천 환경
hyper_clova_seed-1.5b-f16.gguf	3.17 GB	원본 품질 유지 (FP16)	충분한 VRAM/RAM 보유 시
hyper_clova_seed-1.5b-Q4_K_M.gguf	1.00 GB	4비트 양자화 (추천)	일반 PC, 빠른 속도 필요 시

6. 양자화 기술 정보 (Technical Note)

Q4_K_M 양자화는 모델의 성능 저하를 최소화하면서 용량을 약 1/3로 줄인 설정입니다.
저사양 기기나 모바일 환경에서도 원활한 한국어 추론이 가능하도록 최적화되었습니다.

Downloads last month: 28

GGUF

Model size

2B params

Architecture

llama

Hardware compatibility

4-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for kammbo/HyperCLOVAX-SEED-Text-Instruct-1.5B-GGUF

Base model

naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-1.5B

Quantized

(21)

this model