Instructions to use ArliAI/DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArliAI/DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small with Transformers:

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

pipe = pipeline("text-generation", model="ArliAI/DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ArliAI/DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small")
model = AutoModelForCausalLM.from_pretrained("ArliAI/DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ArliAI/DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ArliAI/DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArliAI/DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ArliAI/DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small

SGLang

How to use ArliAI/DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small 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 "ArliAI/DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small" \
    --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": "ArliAI/DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small",
		"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 "ArliAI/DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small" \
        --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": "ArliAI/DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ArliAI/DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small with Docker Model Runner:
```
docker model run hf.co/ArliAI/DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small
```

OwenArli commited on Jun 25, 2025

Commit

99d1bc4

verified ·

1 Parent(s): 0a4ef98

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -0

README.md CHANGED Viewed

@@ -14,6 +14,10 @@ pipeline_tag: text-generation
 <small>Image generated using Arli AI Image Generation https://www.arliai.com/image-generation</small>
 ## RpR v4 Changes:
 The best RP/creative model series from ArliAI yet again. This time made based on DS-R1-0528-Qwen3-8B-Fast for a smaller memory footprint.

 <small>Image generated using Arli AI Image Generation https://www.arliai.com/image-generation</small>
+# Different RpR Versions
+[Small - 8B](https://huggingface.co/ArliAI/DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small) | [Fast - 30B-A3B](https://huggingface.co/ArliAI/Qwen3-30B-A3B-ArliAI-RpR-v4-Fast) | [OG - 32B](https://huggingface.co/ArliAI/QwQ-32B-ArliAI-RpR-v4) | [Large - 70B](https://huggingface.co/ArliAI/DS-R1-Distill-70B-ArliAI-RpR-v4-Large)
 ## RpR v4 Changes:
 The best RP/creative model series from ArliAI yet again. This time made based on DS-R1-0528-Qwen3-8B-Fast for a smaller memory footprint.