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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

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

Use Docker

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

SGLang

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

Docker Model Runner
How to use DataPilot/ArrowPro-7B-RobinHood with Docker Model Runner:
```
docker model run hf.co/DataPilot/ArrowPro-7B-RobinHood
```

Holy-fox commited on May 10, 2024

Commit

dc14c25

verified ·

1 Parent(s): 6ba5b59

11

Browse files

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -1,7 +1,9 @@
 ---
 license: apache-2.0
 ---
-![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/65f01b5235c5424c262c8be8/QGK7V1u4uq9Co_b-EM4Go.jpeg)
 ## 概要
 ArrowPro-7B-RobinHood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。
@@ -10,7 +12,7 @@ ArrowPro-7B-RobinHoodはMistral系のNTQAI/chatntq-ja-7b-v1.0をベースにAItu
 ArrowPro-7B-RobinHoodはベンチマーク(ELYZA-TASK100)において約3.84(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。
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/65f01b5235c5424c262c8be8/xwR2f_msM-mJUAbdmlu4v.png)
 ## How to use
 ```python

 ---
 license: apache-2.0
 ---
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/65f01b5235c5424c262c8be8/AhebtTf7glZA0gr6Pj1ZC.png)
 ## 概要
 ArrowPro-7B-RobinHood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。
 ArrowPro-7B-RobinHoodはベンチマーク(ELYZA-TASK100)において約3.84(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。
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/65f01b5235c5424c262c8be8/kM9-6vTOzXtzvzR4U-jsp.png)
 ## How to use
 ```python