Instructions to use MinimaLabs/min-spark-1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MinimaLabs/min-spark-1.5 with Transformers:

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

pipe = pipeline("text-generation", model="MinimaLabs/min-spark-1.5", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("MinimaLabs/min-spark-1.5", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MinimaLabs/min-spark-1.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MinimaLabs/min-spark-1.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MinimaLabs/min-spark-1.5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MinimaLabs/min-spark-1.5

SGLang

How to use MinimaLabs/min-spark-1.5 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 "MinimaLabs/min-spark-1.5" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MinimaLabs/min-spark-1.5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "MinimaLabs/min-spark-1.5" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MinimaLabs/min-spark-1.5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MinimaLabs/min-spark-1.5 with Docker Model Runner:
```
docker model run hf.co/MinimaLabs/min-spark-1.5
```

min-spark-1.5 / charts /banner.svg

Eclipse-Senpai

card: larger charts, title-only banner

5e0a555 verified 14 days ago

preview code

Raw History Blame Contribute Delete

394 Bytes

<svg xmlns="http://www.w3.org/2000/svg" width="900" height="130" viewBox="0 0 900 130">
  <rect width="900" height="130" rx="14" fill="#0a0a0a"/>
  <text x="450" y="86" text-anchor="middle" font-family="Helvetica, Arial, sans-serif" font-size="60" font-weight="700" fill="#ffffff">min-<tspan fill="#38BDF8">spark</tspan><tspan dx="18" fill="#94a3b8" font-weight="400">1.5</tspan></text>
</svg>

	<svg xmlns="http://www.w3.org/2000/svg" width="900" height="130" viewBox="0 0 900 130">
	<rect width="900" height="130" rx="14" fill="#0a0a0a"/>
	<text x="450" y="86" text-anchor="middle" font-family="Helvetica, Arial, sans-serif" font-size="60" font-weight="700" fill="#ffffff">min-<tspan fill="#38BDF8">spark</tspan><tspan dx="18" fill="#94a3b8" font-weight="400">1.5</tspan></text>
	</svg>