Instructions to use DoppelReflEx/MiniusLight-24B-v2.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DoppelReflEx/MiniusLight-24B-v2.1 with Transformers:

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

pipe = pipeline("text-generation", model="DoppelReflEx/MiniusLight-24B-v2.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DoppelReflEx/MiniusLight-24B-v2.1")
model = AutoModelForCausalLM.from_pretrained("DoppelReflEx/MiniusLight-24B-v2.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DoppelReflEx/MiniusLight-24B-v2.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DoppelReflEx/MiniusLight-24B-v2.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DoppelReflEx/MiniusLight-24B-v2.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DoppelReflEx/MiniusLight-24B-v2.1

SGLang

How to use DoppelReflEx/MiniusLight-24B-v2.1 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-v2.1" \
    --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": "DoppelReflEx/MiniusLight-24B-v2.1",
		"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 "DoppelReflEx/MiniusLight-24B-v2.1" \
        --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": "DoppelReflEx/MiniusLight-24B-v2.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DoppelReflEx/MiniusLight-24B-v2.1 with Docker Model Runner:
```
docker model run hf.co/DoppelReflEx/MiniusLight-24B-v2.1
```

No link

by Topsy1 - opened Apr 27, 2025

Discussion

Topsy1

Apr 27, 2025

Hello, id like to try this model, but the GGUF link goes to V1.01. I cant find V2.1 anywhere.

Topsy1 changed discussion status to closed Apr 27, 2025

Topsy1 changed discussion status to open Apr 27, 2025

DoppelReflEx

Owner Apr 28, 2025

•

edited Apr 28, 2025

@Topsy1 hello, thank you for willing to try this model.
I forgot to change the name and link of GGUF version so that I think you can't find exact version of it.
I have made my own Q4_K_S quant, you could try it: https://huggingface.co/DoppelReflEx/MiniusLight-24B-v2.1-Q4_K_S-GGUF
again, thank you for using my model :)
PS: I think mradermacher will quantize this model in several hours later. I will update the link when he quantized its.

Topsy1

Apr 28, 2025

Thanks! Ill try it when i get home. You made the perfect size for my 4080 too.

DoppelReflEx

Owner Apr 28, 2025

•

edited Apr 29, 2025

You made the perfect size for my 4080 too.

mradermacher and his team is quantizing iMatrix version, you could choose better quant size that suit 4080 like Q4_K_M :)
https://huggingface.co/mradermacher/MiniusLight-24B-v2.1-GGUF
I still working with mradermacher's team and wait they quantize model for me. ~~Will update the link when all quant version completed.~~
Hope I can get feedback from you. Thank you for using my model. XD
PS: All GGUF link updated, I will close this discussion now. XD

DoppelReflEx changed discussion status to closed Apr 29, 2025

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