Instructions to use kistepAI/SPARK-Report-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kistepAI/SPARK-Report-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="kistepAI/SPARK-Report-GGUF",
	filename="kistep-mistral-nemo-report-bf16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use kistepAI/SPARK-Report-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf kistepAI/SPARK-Report-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf kistepAI/SPARK-Report-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf kistepAI/SPARK-Report-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf kistepAI/SPARK-Report-GGUF:BF16

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 kistepAI/SPARK-Report-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf kistepAI/SPARK-Report-GGUF:BF16

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 kistepAI/SPARK-Report-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kistepAI/SPARK-Report-GGUF:BF16

Use Docker

docker model run hf.co/kistepAI/SPARK-Report-GGUF:BF16

LM Studio
Jan

vLLM

How to use kistepAI/SPARK-Report-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/kistepAI/SPARK-Report-GGUF:BF16

Ollama
How to use kistepAI/SPARK-Report-GGUF with Ollama:
```
ollama run hf.co/kistepAI/SPARK-Report-GGUF:BF16
```

Unsloth Studio new

How to use kistepAI/SPARK-Report-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 kistepAI/SPARK-Report-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 kistepAI/SPARK-Report-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kistepAI/SPARK-Report-GGUF to start chatting

Pi new

How to use kistepAI/SPARK-Report-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf kistepAI/SPARK-Report-GGUF:BF16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "kistepAI/SPARK-Report-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use kistepAI/SPARK-Report-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf kistepAI/SPARK-Report-GGUF:BF16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default kistepAI/SPARK-Report-GGUF:BF16

Run Hermes

hermes

Docker Model Runner
How to use kistepAI/SPARK-Report-GGUF with Docker Model Runner:
```
docker model run hf.co/kistepAI/SPARK-Report-GGUF:BF16
```

Lemonade

How to use kistepAI/SPARK-Report-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kistepAI/SPARK-Report-GGUF:BF16

Run and chat with the model

lemonade run user.SPARK-Report-GGUF-BF16

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Usage Guide

개인은 자유롭게 사용할 수 있습니다.
기업 및 기관은 비상업적 목적으로 이용해 주시기 바랍니다.
또한, 추후 협업 및 네트워크 구축을 위해 기관 정보와 AI 모델 사용 담당자 정보를 메일로 보내주시면 연락드리겠습니다.

CONTACT : kistep_ax@kistep.re.kr

Individuals are free to use this without restrictions.
For companies and institutions, please use it for non-commercial purposes.
Additionally, to facilitate future collaboration and network building, please send us an email with your institution's information and the contact details of the person responsible for using the AI model. We will get in touch with you.

1. Description

SPARK-Report is a specialized report writing model developed by the Korea Institute of S&T Evaluation and Planning (KISTEP). The model is trained to generate reports in a two-step process: first creating a table of contents, then generating the main content.

2. Key Features

Content Structure: Generates report outlines based on title, keywords, and desired length
Writing Styles: Capable of producing reports in both descriptive and bullet-point formats
Structured Output: Delivers well-formatted content for enhanced readability
Base Model: Built on Mistral-nemo as the foundation model
Training Method: Trained with Supervised Fine-Tuning (SFT)
Context Length: The maximum context length for training data is 16,384

3. Data

source	KISTEP Document
count	31,058

4. Usage

When using ollama, you can utilize the Modelfile.
Recommended Prompt Template (Table of Contents) (input: {TITLE}, {KEYWORDS}, {LEGNTH})

propmt_template: |
    당신은 보고서 목차 생성 전문가입니다. 주어진 보고서 제목과 키워드를 바탕으로 체계적인 목차를 생성해 주세요.
    
    # 입력정보
    - 제목: {TITLE}
    - 키워드: {KEYWORDS}
    - 분량: {LENGTH}
    
    # 목차 작성 지침
    - 기본구조(head1)는 서론, 본론, 결론으로 구성
    - 각 head1 항목 별로 3-4개의 상세 목차(head2) 생성
    - 키워드를 적극 활용하여 특징적인 표현 사용
    - 시간 표현이나 특수문자 사용 지양
    - 제목 연관성과 전체 일관성 유지
    - 개조식 문체와 명사형 종결어미 사용

Recommended Prompt Template (Main Content) (input: {TITLE}, {SECTIONS}, {SECTION}, {TYPE}, {DOCUMENTS})

propmt_template: |
당신은 보고서 작성 전문가입니다. 보고서 제목은 {TITLE}이며, 전체 목차는 아래와 같습니다:

{SECTIONS}

현재 작성할 섹션은 {SECTION}입니다. 작성 스타일은 {TYPE}을 사용합니다.

주요 지침:
1. 답변은 반드시 아래의 정보만을 사용하여 작성해야 합니다.
{DOCUMENTS}

1. 본문 작성 전에 <reason> 태그 안에 아래 내용을 포함하여 추론 과정을 최대 10문장 이내로 설명하세요:
- 본문 작성에 사용한 청크 인덱스 표기
- 각 청크의 관련 정보 설명
- 필요시 부가적인 제안 사항 (단, 사실확인 필요성 언급 필수)

2. 다음 형식으로 답변을 작성하세요:
- 작성 가능한 경우: <reason>추론 과정</reason> <answer>본문 내용</answer>
- 작성 불가능한 경우: <reason>관련 내용 부재</reason> <answer>제공된 문서를 바탕으로 답변할 수 없습니다.</answer>

서술형(descriptive) 작성 규칙:
- 최대 30문장 이내로 작성
- 문단은 내용에 따라 1~3개로 구성
- 연결어 사용 제한
- 키워드 반복 제한

개조식(bullet_point) 작성 규칙:
□ Level 1: 핵심 내용
◦ Level 2: 하위 내용(1~3개 항목)
- Level 3: 부연 설명

- 마침표 생략
- 간결하고 명확한 문장 구성
- 전문적인 용어 사용
- 의미 단위로 단락 구분

5. Benchmark

TBD

Downloads last month: -

GGUF

Model size

12B params

Architecture

llama

Hardware compatibility

16-bit

Model tree for kistepAI/SPARK-Report-GGUF

Base model

mistralai/Mistral-Nemo-Base-2407

Finetuned

mistralai/Mistral-Nemo-Instruct-2407

Quantized

(173)

this model