Instructions to use ArliAI/DS-R1-Distill-70B-ArliAI-RpR-v4-Large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArliAI/DS-R1-Distill-70B-ArliAI-RpR-v4-Large with Transformers:

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

pipe = pipeline("text-generation", model="ArliAI/DS-R1-Distill-70B-ArliAI-RpR-v4-Large")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ArliAI/DS-R1-Distill-70B-ArliAI-RpR-v4-Large")
model = AutoModelForCausalLM.from_pretrained("ArliAI/DS-R1-Distill-70B-ArliAI-RpR-v4-Large")
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-Distill-70B-ArliAI-RpR-v4-Large with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ArliAI/DS-R1-Distill-70B-ArliAI-RpR-v4-Large"
# 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-Distill-70B-ArliAI-RpR-v4-Large",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ArliAI/DS-R1-Distill-70B-ArliAI-RpR-v4-Large

SGLang

How to use ArliAI/DS-R1-Distill-70B-ArliAI-RpR-v4-Large 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-Distill-70B-ArliAI-RpR-v4-Large" \
    --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-Distill-70B-ArliAI-RpR-v4-Large",
		"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-Distill-70B-ArliAI-RpR-v4-Large" \
        --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-Distill-70B-ArliAI-RpR-v4-Large",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ArliAI/DS-R1-Distill-70B-ArliAI-RpR-v4-Large with Docker Model Runner:
```
docker model run hf.co/ArliAI/DS-R1-Distill-70B-ArliAI-RpR-v4-Large
```

Question about formatting on SillyTavern.

by R136a1 - opened Jun 7, 2025

Discussion

R136a1

Jun 7, 2025

It starts to think even on "personate" user mode on ST. It doesn't happen with other thinking models like qwq and nemotron. How to prevent it?

OwenArli

Arli AI org Jun 15, 2025

This model always needs to think

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment