Instructions to use inclusionAI/Ring-2.5-1T with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inclusionAI/Ring-2.5-1T with Transformers:

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

pipe = pipeline("text-generation", model="inclusionAI/Ring-2.5-1T", 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/Ring-2.5-1T", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use inclusionAI/Ring-2.5-1T with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inclusionAI/Ring-2.5-1T"
# 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/Ring-2.5-1T",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/inclusionAI/Ring-2.5-1T

SGLang

How to use inclusionAI/Ring-2.5-1T 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/Ring-2.5-1T" \
    --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/Ring-2.5-1T",
		"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/Ring-2.5-1T" \
        --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/Ring-2.5-1T",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inclusionAI/Ring-2.5-1T with Docker Model Runner:
```
docker model run hf.co/inclusionAI/Ring-2.5-1T
```

Are IMO results reliable?

by Alicia-Ross - opened Feb 14

Discussion

Alicia-Ross

Feb 14

•

edited Feb 14

https://huggingface.co/inclusionAI/Ring-1T/discussions/5
https://github.com/inclusionAI/AWorld/issues/520

The person raising the question（github） had previously received the Silver Medal at the 58th International Mathematical Olympiad (IMO).

I've noticed that your model continue to promote IMO results, but many people have questions about them, and you haven't seemed to have a formal response.

ZjWen

inclusionAI org Feb 15

Thanks for your question.

You can check this address for more detailed information： https://github.com/inclusionAI/Ring-V2.5/tree/main/examples

Best regards.

Alicia-Ross

Feb 15

@ZjWen
Thank you for your reply.
From your perspective, what is the current level of your proofs for math problems in the IMO? Have you had a professional evaluation?
Does it truly reaches the gold medal level you claim?
As a contestant myself (but not an IMO participant), I have seen your proofs and noticed comments from previous IMO winners regarding your outputs, hence this question.

ZjWen

inclusionAI org Feb 15

The evaluation for IMO25 and CMO25 was confirmed through cross-verification by multiple professional CMO gold medalists, with each problem having an analysis and a final judgment.

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