Instructions to use kueizen/Marco-Mini-Instruct-REAP10 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kueizen/Marco-Mini-Instruct-REAP10 with Transformers:

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

pipe = pipeline("text-generation", model="kueizen/Marco-Mini-Instruct-REAP10")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kueizen/Marco-Mini-Instruct-REAP10")
model = AutoModelForCausalLM.from_pretrained("kueizen/Marco-Mini-Instruct-REAP10", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kueizen/Marco-Mini-Instruct-REAP10 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kueizen/Marco-Mini-Instruct-REAP10"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kueizen/Marco-Mini-Instruct-REAP10",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kueizen/Marco-Mini-Instruct-REAP10

SGLang

How to use kueizen/Marco-Mini-Instruct-REAP10 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 "kueizen/Marco-Mini-Instruct-REAP10" \
    --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": "kueizen/Marco-Mini-Instruct-REAP10",
		"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 "kueizen/Marco-Mini-Instruct-REAP10" \
        --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": "kueizen/Marco-Mini-Instruct-REAP10",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kueizen/Marco-Mini-Instruct-REAP10 with Docker Model Runner:
```
docker model run hf.co/kueizen/Marco-Mini-Instruct-REAP10
```

ThePabli commited on 24 days ago

Commit

14a0189

verified ·

1 Parent(s): 2b73f43

Add model card

Browse files

Files changed (1) hide show

README.md +41 -0

README.md ADDED Viewed

	@@ -0,0 +1,41 @@

+---
+license: apache-2.0
+base_model: ATH-MaaS/Marco-Mini-Instruct
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- moe
+- mixture-of-experts
+- reap
+- expert-pruning
+---
+# Marco-Mini-Instruct-REAP10
+[Marco-Mini-Instruct](https://huggingface.co/ATH-MaaS/Marco-Mini-Instruct) (17.3B total, ~0.86B active, 256 experts, 8 active per token) with **10% of its experts removed** by [REAP](https://arxiv.org/abs/2510.13999): 231 of 256 experts kept. These are the full-precision (bf16) safetensors weights, for fine-tuning, re-quantising or running with `transformers`.
+For ready-to-run quantised files at every pruning ratio, see [kueizen/Marco-Mini-Instruct-REAP-GGUF](https://huggingface.co/kueizen/Marco-Mini-Instruct-REAP-GGUF).
+## Load it
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+repo = "kueizen/Marco-Mini-Instruct-REAP10"
+tok = AutoTokenizer.from_pretrained(repo)
+model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="auto", device_map="auto")
+```
+## How this was made
+- **Pruning:** [REAP](https://arxiv.org/abs/2510.13999) (Router-weighted Expert Activation Pruning, Cerebras Research), using the [reference implementation](https://github.com/CerebrasResearch/reap). REAP scores each expert by its router weight times the size of its output over a calibration set, then removes the lowest-scoring experts whole. It is one-shot: no retraining. Seed 42.
+- **Calibration set:** [theblackcat102/evol-codealpaca-v1](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1) (train split, shuffled, seed 42), 64 samples per category, batch size 1, max sequence length 2048 tokens.
+- **Experts removed:** 10% (231 of 256 kept).
+We have not run task benchmarks on these checkpoints (MMLU, coding, multilingual). Test them on your own workload before relying on them.
+## License and credits
+Derived from [ATH-MaaS/Marco-Mini-Instruct](https://huggingface.co/ATH-MaaS/Marco-Mini-Instruct) and released under the same **Apache 2.0** licence. What we changed: removed experts with REAP. Nothing else was modified or retrained. REAP is by Cerebras Research: [paper](https://arxiv.org/abs/2510.13999), [code](https://github.com/CerebrasResearch/reap). All credit for the base model goes to its authors.
+Published by [Kueizen](https://kueizen.com).