Instructions to use DataPilot/Arrival-32B-Instruct-v0.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DataPilot/Arrival-32B-Instruct-v0.5 with Transformers:

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

pipe = pipeline("text-generation", model="DataPilot/Arrival-32B-Instruct-v0.5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DataPilot/Arrival-32B-Instruct-v0.5")
model = AutoModelForCausalLM.from_pretrained("DataPilot/Arrival-32B-Instruct-v0.5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DataPilot/Arrival-32B-Instruct-v0.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DataPilot/Arrival-32B-Instruct-v0.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DataPilot/Arrival-32B-Instruct-v0.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DataPilot/Arrival-32B-Instruct-v0.5

SGLang

How to use DataPilot/Arrival-32B-Instruct-v0.5 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/Arrival-32B-Instruct-v0.5" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DataPilot/Arrival-32B-Instruct-v0.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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/Arrival-32B-Instruct-v0.5" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DataPilot/Arrival-32B-Instruct-v0.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DataPilot/Arrival-32B-Instruct-v0.5 with Docker Model Runner:
```
docker model run hf.co/DataPilot/Arrival-32B-Instruct-v0.5
```

概要

このモデルはQwQのような長文を出力させるために組んだモデルです。 Mergeをした後で日本語の事後学習をしています。

注意

このモデルは 長考モデルではありません。

How to use

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "DataPilot/Arrival-32B-Instruct-v0.5"
tokenizer_name = ""

if tokenizer_name == "":
    tokenizer_name = model_name

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(tokenizer_name)

prompt = "9.9と9.11はどちらのほうが大きいですか？"
messages = [
    {"role": "system", "content": "あなたは優秀な日本語アシスタントです。問題解決をするために考えた上で回答を行ってください。"},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=1024
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

print(response)

ベンチマーク

このモデルはELYZA-task100で4.63をマークしました。(評価にはGroqのllama3-70B-8192を使用しました。)

謝辞

モデルの作成者であるQwenチーム,karakuri_lmチーム,linkbricksチーム、評価モデルの作成者であるmeta社とAPIを公開しているGroq社、計算資源を貸していただいたVOLTMIND社に感謝を申し上げます。

merge config

merge_method: slerp
base_model: karakuri-ai/karakuri-lm-32b-thinking-2501-exp
models:
  - model: karakuri-ai/karakuri-lm-32b-thinking-2501-exp
  - model: Saxo/Linkbricks-Horizon-AI-Japanese-Base-32B
parameters:
  t: 0.35
dtype: bfloat16
name: DataPilot/Arrival-32B-Instruct-v0.5

Downloads last month: -

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for DataPilot/Arrival-32B-Instruct-v0.5

Saxo/Linkbricks-Horizon-AI-Japanese-Base-32B

karakuri-ai/karakuri-lm-32b-thinking-2501-exp

Merge model

this model

Collection including DataPilot/Arrival-32B-Instruct-v0.5

Arrival_Series

Collection

Qwen2.5をベースとした試作モデルシリーズであるArrivalシリーズのコレクションおよび、当シリーズのために制作されたモデル • 6 items • Updated Jan 29, 2025