Instructions to use XiaoduoAILab/Xmodel-2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XiaoduoAILab/Xmodel-2.5 with Transformers:

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

pipe = pipeline("text-generation", model="XiaoduoAILab/Xmodel-2.5", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("XiaoduoAILab/Xmodel-2.5", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use XiaoduoAILab/Xmodel-2.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XiaoduoAILab/Xmodel-2.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XiaoduoAILab/Xmodel-2.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XiaoduoAILab/Xmodel-2.5

SGLang

How to use XiaoduoAILab/Xmodel-2.5 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 "XiaoduoAILab/Xmodel-2.5" \
    --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": "XiaoduoAILab/Xmodel-2.5",
		"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 "XiaoduoAILab/Xmodel-2.5" \
        --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": "XiaoduoAILab/Xmodel-2.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use XiaoduoAILab/Xmodel-2.5 with Docker Model Runner:
```
docker model run hf.co/XiaoduoAILab/Xmodel-2.5
```

Add `library_name: transformers` to metadata

by nielsr HF Staff - opened Dec 7, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-2

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -3,13 +3,14 @@ language:
 - en
 - zh
 license: apache-2.0
 tags:
 - reasoning
 - small-language-model
 - efficient-training
 - xmodel
 - xiaoduo-ai
-pipeline_tag: text-generation
 ---
 # Xmodel-2.5: 1.3B Data-Efficient Reasoning SLM
@@ -177,4 +178,4 @@ For questions or suggestions, please contact us through:
 ## License
-This project is licensed under the Apache-2.0 License. See the [LICENSE](LICENSE) file for details.

 - en
 - zh
 license: apache-2.0
+pipeline_tag: text-generation
 tags:
 - reasoning
 - small-language-model
 - efficient-training
 - xmodel
 - xiaoduo-ai
+library_name: transformers
 ---
 # Xmodel-2.5: 1.3B Data-Efficient Reasoning SLM
 ## License
+This project is licensed under the Apache-2.0 License. See the [LICENSE](LICENSE) file for details.