Instructions to use fariasultana/MiniMind with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fariasultana/MiniMind with Transformers:

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

pipe = pipeline("text-generation", model="fariasultana/MiniMind", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("fariasultana/MiniMind", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use fariasultana/MiniMind with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/fariasultana/MiniMind

SGLang

How to use fariasultana/MiniMind 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 "fariasultana/MiniMind" \
    --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": "fariasultana/MiniMind",
		"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 "fariasultana/MiniMind" \
        --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": "fariasultana/MiniMind",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fariasultana/MiniMind with Docker Model Runner:
```
docker model run hf.co/fariasultana/MiniMind
```

MiniMind / docker /Dockerfile

fariasultana

feat: Add Docker deployment files

7f36455 verified 6 months ago

raw

history blame contribute delete

1.15 kB

	# MiniMind Max2 - Efficient Edge LLM
	# Docker Hub: sultanafariabd/minimind-max2

	FROM python:3.11-slim

	LABEL maintainer="MiniMind Team <contact@minimind.ai>"
	LABEL org.opencontainers.image.title="MiniMind Max2"
	LABEL org.opencontainers.image.description="Efficient LLM with MoE (8 experts, 25% activation) + GQA"
	LABEL org.opencontainers.image.version="1.0.0"
	LABEL org.opencontainers.image.source="https://huggingface.co/fariasultana/MiniMind"
	LABEL org.opencontainers.image.licenses="Apache-2.0"
	LABEL ai.model.architecture="MoE+GQA"
	LABEL ai.model.parameters="500M-3B"
	LABEL ai.model.active_ratio="25%"

	ENV PYTHONUNBUFFERED=1
	ENV MODEL_VARIANT=max2-nano
	ENV PORT=8000

	WORKDIR /app

	# Install dependencies
	RUN pip install --no-cache-dir \
	torch>=2.1.0 \
	numpy>=1.24.0 \
	fastapi>=0.100.0 \
	uvicorn>=0.23.0 \
	safetensors>=0.4.0 \
	pydantic>=2.0.0

	# Copy application
	COPY serve.py /app/
	COPY model_info.json /app/

	EXPOSE 8000

	HEALTHCHECK --interval=30s --timeout=10s --start-period=30s \
	CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')" \|\| exit 1

	CMD ["python", "serve.py"]