Instructions to use SlimFactoryHub/SlimMoE-250M-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SlimFactoryHub/SlimMoE-250M-instruct with Transformers:

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

pipe = pipeline("text-generation", model="SlimFactoryHub/SlimMoE-250M-instruct", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("SlimFactoryHub/SlimMoE-250M-instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SlimFactoryHub/SlimMoE-250M-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SlimFactoryHub/SlimMoE-250M-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SlimFactoryHub/SlimMoE-250M-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SlimFactoryHub/SlimMoE-250M-instruct

SGLang

How to use SlimFactoryHub/SlimMoE-250M-instruct 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 "SlimFactoryHub/SlimMoE-250M-instruct" \
    --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": "SlimFactoryHub/SlimMoE-250M-instruct",
		"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 "SlimFactoryHub/SlimMoE-250M-instruct" \
        --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": "SlimFactoryHub/SlimMoE-250M-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SlimFactoryHub/SlimMoE-250M-instruct with Docker Model Runner:
```
docker model run hf.co/SlimFactoryHub/SlimMoE-250M-instruct
```

Aispace2001 commited on Dec 31, 2025

Commit

a876969

verified ·

1 Parent(s): cc8b7b2

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -142,7 +142,8 @@ We would like to thank the dataset providers and the open-source community whose
 - **CAIS** for the **MMLU** dataset used for auxiliary knowledge and reasoning supervision.
 - **HuggingFaceTB** for the **OpenHermes-2.5-H4** dataset used in the final instruction refinement phase.
 - **Weights & Biases (W&B)** for logging and visualization tools used to monitor training progress.
 We also acknowledge the broader open-source research community for their continuous efforts in advancing efficient model architectures and training methodologies.

 - **CAIS** for the **MMLU** dataset used for auxiliary knowledge and reasoning supervision.
 - **HuggingFaceTB** for the **OpenHermes-2.5-H4** dataset used in the final instruction refinement phase.
 - **Weights & Biases (W&B)** for logging and visualization tools used to monitor training progress.
+- Additionally, we drew valuable insights from **The Smol Training Playbook: The Secrets to Building World-Class LLMs**, published by Hugging Face, which informed several practical decisions in our training and experimentation workflow.
+Playbook link: https://huggingfacetb-smol-training-playbook.hf.space/the-smol-training-playbook-the-secrets-to-building-world-class-llms.pdf
 We also acknowledge the broader open-source research community for their continuous efforts in advancing efficient model architectures and training methodologies.