Instructions to use QuantFactory/ArrowPro-7B-KUJIRA-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/ArrowPro-7B-KUJIRA-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/ArrowPro-7B-KUJIRA-GGUF",
	filename="ArrowPro-7B-KUJIRA.Q2_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use QuantFactory/ArrowPro-7B-KUJIRA-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/ArrowPro-7B-KUJIRA-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/ArrowPro-7B-KUJIRA-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 QuantFactory/ArrowPro-7B-KUJIRA-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/ArrowPro-7B-KUJIRA-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 QuantFactory/ArrowPro-7B-KUJIRA-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/ArrowPro-7B-KUJIRA-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 QuantFactory/ArrowPro-7B-KUJIRA-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/ArrowPro-7B-KUJIRA-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/ArrowPro-7B-KUJIRA-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/ArrowPro-7B-KUJIRA-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantFactory/ArrowPro-7B-KUJIRA-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantFactory/ArrowPro-7B-KUJIRA-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/QuantFactory/ArrowPro-7B-KUJIRA-GGUF:Q4_K_M

Ollama
How to use QuantFactory/ArrowPro-7B-KUJIRA-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/ArrowPro-7B-KUJIRA-GGUF:Q4_K_M
```

Unsloth Studio new

How to use QuantFactory/ArrowPro-7B-KUJIRA-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 QuantFactory/ArrowPro-7B-KUJIRA-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 QuantFactory/ArrowPro-7B-KUJIRA-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/ArrowPro-7B-KUJIRA-GGUF to start chatting

Docker Model Runner
How to use QuantFactory/ArrowPro-7B-KUJIRA-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/ArrowPro-7B-KUJIRA-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/ArrowPro-7B-KUJIRA-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/ArrowPro-7B-KUJIRA-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.ArrowPro-7B-KUJIRA-GGUF-Q4_K_M

List all available models

lemonade list

QuantFactory/ArrowPro-7B-KUJIRA-GGUF

This is quantied version of DataPilot/ArrowPro-7B-KUJIRA created using llama.cpp

Model Description

ArrowPro-7B-KUJIRAはMistral系のNTQAI/chatntq-ja-7b-v1.0をベースにAItuber、AIアシスタントの魂となるようにChat性能、および高いプロンプトインジェクション耐性を重視して作られました。

ベンチマーク

ArrowPro-7B-KUJIRAはベンチマーク(ELYZA-TASK100)において約3.8(LLaMa3-70B準拠)をマークし、7Bにおいて日本語性能世界一を達成しました。

How to use

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DataPilot/ArrowPro-7B-KUJIRA")
model = AutoModelForCausalLM.from_pretrained(
  "DataPilot/ArrowPro-7B-KUJIRA",
  torch_dtype="auto",
)
model.eval()

if torch.cuda.is_available():
    model = model.to("cuda")

def build_prompt(user_query):
    sys_msg = "あなたは日本語を話す優秀なアシスタントです。回答には必ず日本語で答えてください。"
    template = """[INST] <<SYS>>
{}
<</SYS>>

{}[/INST]"""
    return template.format(sys_msg,user_query)

# Infer with prompt without any additional input
user_inputs = {
    "user_query": "まどマギで一番かわいいキャラはだれ？",
}
prompt = build_prompt(**user_inputs)

input_ids = tokenizer.encode(
    prompt, 
    add_special_tokens=True, 
    return_tensors="pt"
)

tokens = model.generate(
    input_ids.to(device=model.device),
    max_new_tokens=500,
    temperature=1,
    top_p=0.95,
    do_sample=True,
)

out = tokenizer.decode(tokens[0][input_ids.shape[1]:], skip_special_tokens=True).strip()
print(out)

謝辞

助言を与えてくださったすべての皆様に感謝します。また、元モデルの開発者の皆様にも感謝を申し上げます。

お願い

このモデルを利用する際は他人に迷惑をかけないように最大限留意してください。

Downloads last month: 80

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for QuantFactory/ArrowPro-7B-KUJIRA-GGUF

Base model

DataPilot/ArrowPro-7B-KUJIRA

Quantized

(2)

this model