Instructions to use fal/moondream2-docci-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fal/moondream2-docci-instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="fal/moondream2-docci-instruct", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("fal/moondream2-docci-instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use fal/moondream2-docci-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fal/moondream2-docci-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fal/moondream2-docci-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fal/moondream2-docci-instruct

SGLang

How to use fal/moondream2-docci-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 "fal/moondream2-docci-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": "fal/moondream2-docci-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 "fal/moondream2-docci-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": "fal/moondream2-docci-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fal/moondream2-docci-instruct with Docker Model Runner:
```
docker model run hf.co/fal/moondream2-docci-instruct
```

Fine tuned version of moondream2 model using gokaygokay/random_instruct_docci dataset. Which gives extremely detailed captions of the images.

pip install transformers timm einops bitsandbytes accelerate flash-attn

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from PIL import Image

DEVICE = "cuda"
DTYPE = (
    torch.float32 if DEVICE == "cpu" else torch.float16
)  # CPU doesn't support float16
revision = "3ec40c7b6b5d87bc0c51edee45e21f5f29b449d8"
tokenizer = AutoTokenizer.from_pretrained(
    "fal-ai/moondream2-docci-instruct",
    trust_remote_code=True,
    revision=revision
)
moondream = AutoModelForCausalLM.from_pretrained(
    "fal-ai/moondream2-docci-instruct",
    trust_remote_code=True,
    torch_dtype=DTYPE,
    device_map={"": DEVICE},
    attn_implementation="flash_attention_2",
    revision=revision
)
moondream.eval()

image_path = "<your_image_path>"
image = Image.open(image_path).convert("RGB")
md_answer = moondream.answer_question(
    moondream.encode_image(image),
    "what is this picture about",
    tokenizer=tokenizer,
)

print(md_answer)

Downloads last month: 9

Safetensors

Model size

2B params

Tensor type

F16

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

fal
/

moondream2-docci-instruct

Datasets used to train fal/moondream2-docci-instruct