Instructions to use DataPilot/ArrowCanaria-Llama-8B-SFT-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DataPilot/ArrowCanaria-Llama-8B-SFT-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="DataPilot/ArrowCanaria-Llama-8B-SFT-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DataPilot/ArrowCanaria-Llama-8B-SFT-v0.1")
model = AutoModelForCausalLM.from_pretrained("DataPilot/ArrowCanaria-Llama-8B-SFT-v0.1", device_map="auto")
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 Settings

vLLM

How to use DataPilot/ArrowCanaria-Llama-8B-SFT-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DataPilot/ArrowCanaria-Llama-8B-SFT-v0.1"
# 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/ArrowCanaria-Llama-8B-SFT-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DataPilot/ArrowCanaria-Llama-8B-SFT-v0.1

SGLang

How to use DataPilot/ArrowCanaria-Llama-8B-SFT-v0.1 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/ArrowCanaria-Llama-8B-SFT-v0.1" \
    --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/ArrowCanaria-Llama-8B-SFT-v0.1",
		"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/ArrowCanaria-Llama-8B-SFT-v0.1" \
        --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/ArrowCanaria-Llama-8B-SFT-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DataPilot/ArrowCanaria-Llama-8B-SFT-v0.1 with Docker Model Runner:
```
docker model run hf.co/DataPilot/ArrowCanaria-Llama-8B-SFT-v0.1
```

Holy-fox commited on Mar 20

Commit

aaab5f5

verified ·

1 Parent(s): e6bfcd3

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -3

README.md CHANGED Viewed

@@ -238,6 +238,9 @@ Phase 3 では RP・クリエイティブという **スタイル転移力の強
 ## 謝辞
-- [tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5) — ベースモデル
-- [Unsloth](https://github.com/unslothai/unsloth) — 高速 LoRA 学習フレームワーク
-- [TRL](https://github.com/huggingface/trl) — SFTTrainer

 ## 謝辞
+- 質の高い日本語モデルを作成してくれたSwallowチームに感謝します。 - [tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5)
+- 高品質なベースモデルを作成してくれたMetaのLlamaチームに感謝します。 - [Meta Llama](https://www.llama.com)
+- 高効率な学習フレームワークを作成してくださったUnslothに感謝します。 - [Unsloth](https://github.com/unslothai/unsloth)
+- そのほか、高品質なデータを作成する際にDeepSeek-V3.2とkimi K2.5を使用しました。[DeepSeekチーム](https://www.deepseek.com)と[Kimiチーム](https://www.moonshot.ai)に感謝します。
+Built by Kimi