Instructions to use XHToken/Spark-X2.5-4B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XHToken/Spark-X2.5-4B-Base with Transformers:

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

pipe = pipeline("text-generation", model="XHToken/Spark-X2.5-4B-Base", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("XHToken/Spark-X2.5-4B-Base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use XHToken/Spark-X2.5-4B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XHToken/Spark-X2.5-4B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XHToken/Spark-X2.5-4B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XHToken/Spark-X2.5-4B-Base

SGLang

How to use XHToken/Spark-X2.5-4B-Base 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 "XHToken/Spark-X2.5-4B-Base" \
    --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": "XHToken/Spark-X2.5-4B-Base",
		"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 "XHToken/Spark-X2.5-4B-Base" \
        --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": "XHToken/Spark-X2.5-4B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use XHToken/Spark-X2.5-4B-Base with Docker Model Runner:
```
docker model run hf.co/XHToken/Spark-X2.5-4B-Base
```

Turn off thinking mode

by Techlogic - opened about 19 hours ago

Discussion

Techlogic

about 19 hours ago

•

edited about 19 hours ago

Hey yes is there a way to turn off the thinking mode in the system prompt? Because I want to use this for creative tasks like rp etc? Thanks!

jxd1999

SparkLLM org about 18 hours ago

•

edited about 18 hours ago

Yes, you can control the thinking mode directly through the prompt formatting. Our model determines whether to enable or disable the "thinking" phase based on the presence of or at the end of the user context.To enable thinking mode, end the conversation prefix with "<think>" .
Example:
<｜start▁of▁sentence｜><|System|>\nyou are a helpful assistant.<｜end▁of▁sentence｜><｜start▁of▁sentence｜><|User|>Where is the provincial capital of Anhui Province?<｜end▁of▁sentence｜><｜start▁of▁sentence｜><|Bot|><think>

To disable thinking mode, simply replace that "<think>" with "</think>" at the same position.
Example:
<｜start▁of▁sentence｜><|System|>\nyou are a helpful assistant.<｜end▁of▁sentence｜><｜start▁of▁sentence｜><|User|>Where is the provincial capital of Anhui Province?<｜end▁of▁sentence｜><｜start▁of▁sentence｜><|Bot|></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