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

Libraries

How to use DataPilot/ArrowPro-7B-KUJIRA with Transformers:

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

pipe = pipeline("text-generation", model="DataPilot/ArrowPro-7B-KUJIRA")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/DataPilot/ArrowPro-7B-KUJIRA

SGLang

How to use DataPilot/ArrowPro-7B-KUJIRA 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 "DataPilot/ArrowPro-7B-KUJIRA" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DataPilot/ArrowPro-7B-KUJIRA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "DataPilot/ArrowPro-7B-KUJIRA" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DataPilot/ArrowPro-7B-KUJIRA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DataPilot/ArrowPro-7B-KUJIRA with Docker Model Runner:
```
docker model run hf.co/DataPilot/ArrowPro-7B-KUJIRA
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

概要

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: 16

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for DataPilot/ArrowPro-7B-KUJIRA

Merges

2 models

Quantizations

2 models