Instructions to use inclusionAI/Ring-lite-distill-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inclusionAI/Ring-lite-distill-preview with Transformers:

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

pipe = pipeline("text-generation", model="inclusionAI/Ring-lite-distill-preview", 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-lite-distill-preview", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use inclusionAI/Ring-lite-distill-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inclusionAI/Ring-lite-distill-preview"
# 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-lite-distill-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/inclusionAI/Ring-lite-distill-preview

SGLang

How to use inclusionAI/Ring-lite-distill-preview 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-lite-distill-preview" \
    --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-lite-distill-preview",
		"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-lite-distill-preview" \
        --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-lite-distill-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inclusionAI/Ring-lite-distill-preview with Docker Model Runner:
```
docker model run hf.co/inclusionAI/Ring-lite-distill-preview
```

Add library_name and paper link

by nielsr HF Staff - opened Apr 11, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-4

Files changed (1) hide show

README.md +7 -4

README.md CHANGED Viewed

@@ -1,11 +1,12 @@
 ---
-license: mit
 language:
 - zh
 - en
-base_model:
-- inclusionAI/Ling-lite
 pipeline_tag: text-generation
 ---
 # Ring-lite-distill-preview
@@ -22,6 +23,8 @@ pipeline_tag: text-generation
 Ring-lite-distill-preview is an MoE LLM provided and open-sourced by InclusionAI, which has 16.8B parameters with 2.75B activated parameters. It was fine-tuned from [Ling-lite](https://modelscope.cn/models/inclusionAI/Ling-lite) using extensive reasoning-focused instruction data. This model delivers performance comparable to DeepSeek-R1-Distill-Qwen-7B on reasoning benchmarks while achieving better results on general benchmarks, especially superior performance on function-calling evaluation benchmarks (e.g., TEval, BFCl_v2) and instruction-following benchmarks (e.g., IFEval). This demonstrates that Ring-lite-distill is a more balanced and versatile model. Additionaly, it maintains competitive latency and throughput compared to other reasoning LLMs of similar size.
 ## Model Downloads
 <div align="center">
@@ -108,4 +111,4 @@ Please refer to [Github](https://github.com/inclusionAI/Ring/blob/main/README.md
 This code repository is licensed under [the MIT License](https://huggingface.co/inclusionAI/Ring-lite-distill/blob/main/LICENSE).
 ## Citation
-[TBD]

 ---
+base_model:
+- inclusionAI/Ling-lite
 language:
 - zh
 - en
+license: mit
 pipeline_tag: text-generation
+library_name: transformers
 ---
 # Ring-lite-distill-preview
 Ring-lite-distill-preview is an MoE LLM provided and open-sourced by InclusionAI, which has 16.8B parameters with 2.75B activated parameters. It was fine-tuned from [Ling-lite](https://modelscope.cn/models/inclusionAI/Ling-lite) using extensive reasoning-focused instruction data. This model delivers performance comparable to DeepSeek-R1-Distill-Qwen-7B on reasoning benchmarks while achieving better results on general benchmarks, especially superior performance on function-calling evaluation benchmarks (e.g., TEval, BFCl_v2) and instruction-following benchmarks (e.g., IFEval). This demonstrates that Ring-lite-distill is a more balanced and versatile model. Additionaly, it maintains competitive latency and throughput compared to other reasoning LLMs of similar size.
+The model was presented in the paper [](https://huggingface.co/papers/2504.07158).
 ## Model Downloads
 <div align="center">
 This code repository is licensed under [the MIT License](https://huggingface.co/inclusionAI/Ring-lite-distill/blob/main/LICENSE).
 ## Citation
+[TBD]