Instructions to use mehmetkeremturkcan/FemtoVLM-Small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mehmetkeremturkcan/FemtoVLM-Small with Transformers:

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

pipe = pipeline("image-text-to-text", model="mehmetkeremturkcan/FemtoVLM-Small")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mehmetkeremturkcan/FemtoVLM-Small", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mehmetkeremturkcan/FemtoVLM-Small with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mehmetkeremturkcan/FemtoVLM-Small

SGLang

How to use mehmetkeremturkcan/FemtoVLM-Small 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 "mehmetkeremturkcan/FemtoVLM-Small" \
    --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": "mehmetkeremturkcan/FemtoVLM-Small",
		"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 "mehmetkeremturkcan/FemtoVLM-Small" \
        --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": "mehmetkeremturkcan/FemtoVLM-Small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mehmetkeremturkcan/FemtoVLM-Small with Docker Model Runner:
```
docker model run hf.co/mehmetkeremturkcan/FemtoVLM-Small
```

mehmetkeremturkcan/FemtoVLM-Small

FemtoVLM: Tiniest Vision Language Models

FemtoVLM is the smallest visual question answering/captioning model in the world. It accepts image and text inputs to produce text outputs. It's designed for efficiency. FemtoVLM can answer questions about images and describe visual content. Its lightweight architecture makes it suitable for on-device applications while maintaining strong performance.

FemtoVLM comes in three sizes: 116M (femto), 143M (tiny), 160M (base), 225M (dino). All models are trained for image captioning and question answering in real-world contexts. FemtoVLM cannot perform optical character recognition (OCR), multi-turn question-answering, or scientific question answering.

Setup

pip install git+https://github.com/facebookresearch/schedule_free.git
pip install peft
git clone https://github.com/mkturkcan/seers.git
cd seers/seers/
git clone https://huggingface.co/mehmetkeremturkcan/FemtoVLM-Small