Instructions to use careerbot/shukatsu-gemma4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use careerbot/shukatsu-gemma4 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="careerbot/shukatsu-gemma4",
	filename="gemma-4-26b-a4b-it.BF16-00002-of-00002.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 careerbot/shukatsu-gemma4 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf careerbot/shukatsu-gemma4:BF16
# Run inference directly in the terminal:
llama-cli -hf careerbot/shukatsu-gemma4:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf careerbot/shukatsu-gemma4:BF16
# Run inference directly in the terminal:
llama-cli -hf careerbot/shukatsu-gemma4: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 careerbot/shukatsu-gemma4:BF16
# Run inference directly in the terminal:
./llama-cli -hf careerbot/shukatsu-gemma4: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 careerbot/shukatsu-gemma4:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf careerbot/shukatsu-gemma4:BF16

Use Docker

docker model run hf.co/careerbot/shukatsu-gemma4:BF16

LM Studio
Jan

vLLM

How to use careerbot/shukatsu-gemma4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "careerbot/shukatsu-gemma4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "careerbot/shukatsu-gemma4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/careerbot/shukatsu-gemma4:BF16

Ollama
How to use careerbot/shukatsu-gemma4 with Ollama:
```
ollama run hf.co/careerbot/shukatsu-gemma4:BF16
```

Unsloth Studio

How to use careerbot/shukatsu-gemma4 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 careerbot/shukatsu-gemma4 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 careerbot/shukatsu-gemma4 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for careerbot/shukatsu-gemma4 to start chatting

How to use careerbot/shukatsu-gemma4 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf careerbot/shukatsu-gemma4: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": "careerbot/shukatsu-gemma4:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use careerbot/shukatsu-gemma4 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf careerbot/shukatsu-gemma4: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 careerbot/shukatsu-gemma4:BF16

Run Hermes

hermes

Docker Model Runner
How to use careerbot/shukatsu-gemma4 with Docker Model Runner:
```
docker model run hf.co/careerbot/shukatsu-gemma4:BF16
```

Lemonade

How to use careerbot/shukatsu-gemma4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull careerbot/shukatsu-gemma4:BF16

Run and chat with the model

lemonade run user.shukatsu-gemma4-BF16

List all available models

lemonade list

shukatsu-gemma4-26b-v1

*このモデルはGoogleのGemma 4を微調整したものであり、Googleの公式製品ではありません。

概要 (Overview)

shukatsu-gemma4 は、就職活動のサポートに特化したAIモデルです。プロのキャリアアドバイザーの「論理的なアドバイス」と「親身なサポート」を再現するように学習されています。

開発: 株式会社キャリアボット
ベースモデル: Google Gemma 4 26B (MoE)
学習手法: Unsloth を使用した高品質データによるファインチューニング

できること (Use Cases)

用途に合わせて、以下のような具体的なサポートが可能です。

ESの論理的な添削: 作成済みのエントリーシートに対し、単なる文章校正にとどまらず「説得力があるか」「論理破綻がないか」をプロの視点でフィードバックします。
自己分析の壁打ち: 対話を通じて、自分では気づきにくい「強み」や「仕事への価値観」を言語化します。
一般的な進路・キャリア相談: 業界選びの軸や就活の進め方、面接に向けた考え方など、就職活動全般の悩みにお答えします。

ダウンロードと使い方 (Usage)

本モデルはGGUF形式です。用途やPCのスペックに合わせてファイルを選択し、llama.cpp や LM Studio などでローカル実行できます。

ファイル名	おすすめの用途	サイズ
`...26b-a4b-it.Q6_K.gguf`	【推奨】高精度に回答させたい場合	22.6 GB
`...e4b-v2.gguf`	精度と軽さのバランス重視	5.34 GB
`...e2b-Q4_0.gguf`	とにかく軽く・速く動かしたい場合	3.36 GB

プロンプトのコツ (Prompting Tips)

システムプロンプト（AIへの事前指示）では、「就活支援のスペシャリスト」としての役割を与え、振る舞いや伝え方を設定すると、より高い精度のフィードバックが得られます。

設定の例:

「あなたは就活支援のスペシャリスト（プロのキャリアアドバイザー）です。親身に寄り添いつつ、論理的にアドバイスしてください。回答は結論から述べ、修正案を出すときは『なぜその修正が必要か』の理由もセットで伝えてください。」

ご注意 (Disclaimer)

AIの回答はあくまで参考情報であり、ハルシネーション（不正確な情報）が含まれる可能性があります。選考の通過を保証するものではありませんので、最終的な判断はご自身で行ってください。

English Summary

shukatsu-gemma4 is an LLM fine-tuned specifically for job hunting (Shukatsu) support in Japan. Based on Gemma 4 26B, it provides logical and empathetic feedback for proofreading Entry Sheets, structuring self-promotions, and assisting with self-analysis and general career consultation. Available in GGUF format for local inference. When prompting, we recommend setting the system persona to a "professional career advisor" for best results. Please verify all AI-generated advice, as it does not guarantee hiring success. *This model is a fine-tuned version of Google's Gemma 4 and is not an official Google product.

Downloads last month: 93

GGUF

Model size

25B params

Architecture

gemma4

Hardware compatibility

4-bit

6-bit

16-bit

View +1 variant