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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DataPilot/ArrowPro-7B-Nyan"
# 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-Nyan",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use DataPilot/ArrowPro-7B-Nyan 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-Nyan" \
    --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-Nyan",
		"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-Nyan" \
        --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-Nyan",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

概要

当モデルはMistral系のArrowPro-7B-KUJIRAをもとにdatabricks-dolly-15k-Nyan-jaを用いて語尾を「にゃん！」にするファインチューニングを実施したモデルとなります。

How to use

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

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

このモデルを作成するために計算資源を貸してくれたwitness氏とMeta Data Labに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: 4

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for DataPilot/ArrowPro-7B-Nyan

Quantizations

1 model