Instructions to use inclusionAI/Ling-1T with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inclusionAI/Ling-1T with Transformers:

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

pipe = pipeline("text-generation", model="inclusionAI/Ling-1T", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("inclusionAI/Ling-1T", trust_remote_code=True, dtype="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use inclusionAI/Ling-1T with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inclusionAI/Ling-1T"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "inclusionAI/Ling-1T",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/inclusionAI/Ling-1T

SGLang

How to use inclusionAI/Ling-1T 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 "inclusionAI/Ling-1T" \
    --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": "inclusionAI/Ling-1T",
		"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 "inclusionAI/Ling-1T" \
        --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": "inclusionAI/Ling-1T",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inclusionAI/Ling-1T with Docker Model Runner:
```
docker model run hf.co/inclusionAI/Ling-1T
```

Ring and Ling differences?

#13

by b-a-s-e-d - opened Oct 21, 2025

Discussion

b-a-s-e-d

Oct 21, 2025

Hi, what is the difference between Ring and Ling? They both have reasoning.

I have read the readme's several times and it's still not very clear.

The only thing that it really says is that Ring is based on Ling Base, but not the actual differences.

RichardBian

inclusionAI org Oct 21, 2025

Hi, thanks for the question. Ling is positioned as a general versatile model similar to DS V3, and Ring is positioned as a specialized reasoning model like DS R1.
That said, we trained Ling with 20T tokens of high-quality, high-reasoning-density corpus, but the model is trained and saved as a non-reasoning model so we could achieve a balance of "efficient thinking, and precise inference". (see the technical article https://ant-ling.medium.com/deep-insight-efficient-inference-introducing-the-trillion-parameter-ling-1t-model-77d6170e5e8e)

You can try the models side by side on ZenMux for the same query to experience the difference.
https://zenmux.ai/inclusionai/ling-1t
https://zenmux.ai/inclusionai/ring-1t

We do have a full-fledged technical report out soon. Hope it'll answer more of your questions.

Best

b-a-s-e-d

Oct 21, 2025

Thank you @RichardBian , now I understand the differences.
I'm impressed by your work and I look forward to the technical report.

zzqsmall changed discussion status to closed Oct 27, 2025

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