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

Libraries

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

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

pipe = pipeline("text-generation", model="DoppelReflEx/MiniusLight-24B-v2")
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")
model = AutoModelForCausalLM.from_pretrained("DoppelReflEx/MiniusLight-24B-v2")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

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

SGLang

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

Docker Model Runner
How to use DoppelReflEx/MiniusLight-24B-v2 with Docker Model Runner:
```
docker model run hf.co/DoppelReflEx/MiniusLight-24B-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

MiniusLight-24B-v2

12B - 24B-v1 - 24B-v1.01 - 24B-v2 - 24B-v2.1

Origin Content (Click Here)

What is this?

A merge of most uncensored model TroyDoesAI/BlackSheep-24B and MiniusLight-24B.

Because OpenLLM Leaderboard closed, I can't test eval anymore but need push more effort in manual test. Good writing style, but not completely uncensored.

Overall, nice to try model, if you want to try. :)

GGUF (Thank mradermacher and his team so much (especially nicoboss))

Static - iMatrix

Other information

Chat Template? ChatML, of course!

Merge Method

Detail YAML Config

  {
  models:
   - model: TroyDoesAI/BlackSheep-24B
     parameters:
       density: 0.9
       weight: 1
   - model: DoppelReflEx/MiniusLight-24B
     parameters:
       density: 0.6
       weight: 0.8
  merge_method: dare_ties
  base_model: TroyDoesAI/BlackSheep-24B
  tokenizer_source: base
  }

Downloads last month: 8

Safetensors

Model size

24B params

Tensor type

BF16

F16

Model tree for DoppelReflEx/MiniusLight-24B-v2

DoppelReflEx/MiniusLight-24B

TroyDoesAI/BlackSheep-24B

Merge model

this model

Quantizations

3 models

Collection including DoppelReflEx/MiniusLight-24B-v2

Nocturne

Collection

Balance size model with good quality. • 6 items • Updated Sep 11, 2025 • 1

DoppelReflEx
/

MiniusLight-24B-v2

MiniusLight-24B-v2

12B - 24B-v1 - 24B-v1.01 - 24B-v2 - 24B-v2.1

What is this?

GGUF (Thank mradermacher and his team so much (especially nicoboss))

Static - iMatrix

Other information

Chat Template? ChatML, of course!

Merge Method

Detail YAML Config

{ models: - model: TroyDoesAI/BlackSheep-24B parameters: density: 0.9 weight: 1 - model: DoppelReflEx/MiniusLight-24B parameters: density: 0.6 weight: 0.8 merge_method: dare_ties base_model: TroyDoesAI/BlackSheep-24B tokenizer_source: base }

Model tree for DoppelReflEx/MiniusLight-24B-v2

Collection including DoppelReflEx/MiniusLight-24B-v2

Nocturne

MiniusLight-24B-v2

12B - 24B-v1 - 24B-v1.01 - 24B-v2 - 24B-v2.1

What is this?

GGUF (Thank mradermacher and his team so much (especially nicoboss))

Static - iMatrix

Other information

Chat Template? ChatML, of course!

Merge Method

Detail YAML Config { models: - model: TroyDoesAI/BlackSheep-24B parameters: density: 0.9 weight: 1 - model: DoppelReflEx/MiniusLight-24B parameters: density: 0.6 weight: 0.8 merge_method: dare_ties base_model: TroyDoesAI/BlackSheep-24B tokenizer_source: base }

Model tree for DoppelReflEx/MiniusLight-24B-v2

Collection including DoppelReflEx/MiniusLight-24B-v2

Detail YAML Config

{ models: - model: TroyDoesAI/BlackSheep-24B parameters: density: 0.9 weight: 1 - model: DoppelReflEx/MiniusLight-24B parameters: density: 0.6 weight: 0.8 merge_method: dare_ties base_model: TroyDoesAI/BlackSheep-24B tokenizer_source: base }