Instructions to use DoppelReflEx/MiniusLight-24B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DoppelReflEx/MiniusLight-24B with Transformers:

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

pipe = pipeline("text-generation", model="DoppelReflEx/MiniusLight-24B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DoppelReflEx/MiniusLight-24B")
model = AutoModelForCausalLM.from_pretrained("DoppelReflEx/MiniusLight-24B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DoppelReflEx/MiniusLight-24B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DoppelReflEx/MiniusLight-24B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DoppelReflEx/MiniusLight-24B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DoppelReflEx/MiniusLight-24B

SGLang

How to use DoppelReflEx/MiniusLight-24B 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 "DoppelReflEx/MiniusLight-24B" \
    --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": "DoppelReflEx/MiniusLight-24B",
		"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 "DoppelReflEx/MiniusLight-24B" \
        --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": "DoppelReflEx/MiniusLight-24B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DoppelReflEx/MiniusLight-24B with Docker Model Runner:
```
docker model run hf.co/DoppelReflEx/MiniusLight-24B
```

DoppelReflEx commited on Mar 15, 2025

Commit

bb6d93b

verified ·

1 Parent(s): 3c98dd6

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -0

README.md CHANGED Viewed

@@ -124,6 +124,10 @@ license: cc-by-nc-4.0
           <p>Overall, nice to try model, if you want to try. :)</p>
         </div>
       </div>
       <div class="border-custom-dot">
         <h2 class="soft-blue-custom">Other information</h2>
         <div class="as">

           <p>Overall, nice to try model, if you want to try. :)</p>
         </div>
       </div>
+      <div class="border-custom-dot mb">
+        <h2 class="soft-blue-custom">GGUF</h2>
+        <h3 class="accent"><a href="https://huggingface.co/mradermacher/MiniusLight-24B-GGUF" class="accent bold">Static</a> - <a class="accent bold" href="https://huggingface.co/mradermacher/MiniusLight-24B-i1-GGUF">iMatrix</a></h3>
+      </div>
       <div class="border-custom-dot">
         <h2 class="soft-blue-custom">Other information</h2>
         <div class="as">