allenai / Molmo-72B-0924

Molmo 72B

Molmo is a family of open vision-language models developed by the Allen Institute for AI. Molmo models are trained on PixMo, a dataset of 1 million, highly-curated image-text pairs. It has state-of-the-art performance among multimodal models with a similar size while being fully open-source. You can find all models in the Molmo family here . Learn more about the Molmo family in our announcement blog post .

Molmo 72B is based on Qwen2-72B and uses OpenAI CLIP as vision backbone. Molmo-72B achieves the highest academic benchmark score and ranks second on human evaluation, just slightly behind GPT-4o.

This checkpoint is a preview of the Molmo release. All artifacts used in creating Molmo (PixMo dataset, training code, evaluations, intermediate checkpoints) will be made available at a later date, furthering our commitment to open-source AI development and reproducibility.

Sign up here to be the first to know when artifacts are released.

Quick links:

• 💬 Demo
• 📂 All Models
• 📃 Paper
• 🎥 Blog with Videos

Quick Start

To run Molmo, first install dependencies:

# uninstall all tensorflow packages
pip list --format=freeze | grep '^tensorflow' | cut -d= -f1 | xargs -n1 pip uninstall -y

# install CPU-only version of tensorflow; used for image preprocessing
pip install einops tensorflow-cpu torchvision

Then, follow these steps:

from transformers import AutoModelForCausalLM, AutoProcessor, GenerationConfig
from PIL import Image
import requests

# load the processor
processor = AutoProcessor.from_pretrained(
    'allenai/Molmo-72B-0924',
    trust_remote_code=True,
    torch_dtype='auto',
    device_map='auto'
)

# load the model
model = AutoModelForCausalLM.from_pretrained(
    'allenai/Molmo-72B-0924',
    trust_remote_code=True,
    torch_dtype='auto',
    device_map='auto'
)

# process the image and text
inputs = processor.process(
    images=[Image.open(requests.get("https://picsum.photos/id/237/536/354", stream=True).raw)],
    text="Describe this image."
)

# move inputs to the correct device and make a batch of size 1
inputs = {k: v.to(model.device).unsqueeze(0) for k, v in inputs.items()}

# generate output; maximum 200 new tokens; stop generation when <|endoftext|> is generated
output = model.generate_from_batch(
    inputs,
    GenerationConfig(max_new_tokens=200, stop_strings="<|endoftext|>"),
    tokenizer=processor.tokenizer
)

# only get generated tokens; decode them to text
generated_tokens = output[0,inputs['input_ids'].size(1):]
generated_text = processor.tokenizer.decode(generated_tokens, skip_special_tokens=True)

# print the generated text
print(generated_text)

# >>> This image features an adorable black Labrador puppy sitting on a wooden deck. 
#     The puppy is positioned in the center of the frame, looking up at the camera...

Evaluations

Benchmarks: AI2D test, ChartQA test, VQA v2.0 test, DocQA test, InfographicVQA test, TextVQA val, RealWorldQA, MMMU val, MathVista testmini, CountBenchQA, Flickr Count (we collected this new dataset that is significantly harder than CountBenchQA).

License and Use

This model is licensed under Apache 2.0. It is intended for research and educational use. For more information, please see our Responsible Use Guidelines .