Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Code for the Molmo Vision-Language Model
| Date | Stars |
|---|---|
| 2026-07-31 | 923 |
| 2026-08-06 | 923 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<img src="assets/Molmo-logo.svg" alt="Molmo Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
<br>
<br>
<h1>Molmo: Multimodal Open Language Model</h1>
</div>
<p align="center">
<a href="https://github.com/allenai/mm_olmo/blob/release/LICENSE">
<img alt="GitHub License" src="https://img.shields.io/github/license/allenai/OLMo">
</a>
<a href="https://molmo.allenai.org/blog">
<img alt="Blog Post" src="https://img.shields.io/badge/Molmo-blog-F0529C">
</a>
<a href="https://arxiv.org/pdf/2409.17146">
<img alt="Paper URL" src="https://img.shields.io/badge/arxiv-2409.17146-blue">
</a>
<a href="https://huggingface.co/collections/allenai/molmo-66f379e6fe3b8ef090a8ca19">
<img alt="Model Checkpoints" src="https://img.shields.io/badge/%F0%9F%A4%97%20HF-Models-yellow">
</a>
<a href="https://huggingface.co/collections/allenai/pixmo-674746ea613028006285687b">
<img alt="PixMo (Datasets)" src="https://img.shields.io/badge/%F0%9F%A4%97%20HF-PixMo (Datasets)-yellow">
</a>
</p>
Molmo is a repository for training and using Ai2's state-of-the-art multimodal open language models.
Here is a **[video demo](https://www.youtube.com/watch?v=spBxYa3eAlA)** of Molmo's capabilities. Try Molmo using our public **[demo](https://molmo.allenai.org)** showcasing the Molmo-7B-D model.
This codebase is based on the [OLMo codebase](https://github.com/allenai/OLMo) with the addition
of vision encoding and integrating generative evaluations.
## Release Notes
- [2024/12/05] **🔥 Molmo**: code for modeling, training and evaluation has been released. You can find detailed technical report [here](https://arxiv.org/pdf/2409.17146).
- [2024/11/27] **🔥 [PixMo](https://huggingface.co/collections/allenai/pixmo-674746ea613028006285687b)**, our new collection of datasets for pre-training and fine-tuning VLMs, has been released. PixMo consists of:
- [**PixMo-Cap**](https://huggingface.co/datasets/allenai/pixmo-cap) (pre-training, fine-tuning): highly detailed dense caption dataset (roughly 200 words on average)
- [**PixMo-AskModelAnything**](https://huggingface.co/datasets/allenai/pixmo-ask-model-anything) (fine-tuning): instruction-tuning data containing human-authored image-question-answer triplets
- [**PixMo-CapQA**](https://huggingface.co/datasets/allenai/pixmo-cap-qa) (fine-tuning): synthetic instruction-tuning data, using a LLM to build QA pairs from dense captions of images
- [**PixMo-Points**](https://huggingface.co/datasets/allenai/pixmo-points) (fine-tuning): images paired with referring expressions and annotated points, supporting grounding and counting
- [**PixMo-Point-Explanations**](https://huggingface.co/datasets/allenai/pixmo-point-explanations) (fine-tuning): instruction-tuning data with explanations containing in-line points referring to parts of the image
- [**PixMo-Docs**](https://huggingface.co/datasets/allenai/pixmo-docs) (fine-tuning): synthetic image-question-answer triplets about various kinds of computer-generated charts, tables, diagrams and documents. Code available [here](https://github.com/allenai/pixmo-docs).
- [**PixMo-Clocks**](https://huggingface.co/datasets/allenai/pixmo-clocks) (fine-tuning): virtual watch faces and time annotations
- [**PixMo-Count**](https://huggingface.co/datasets/allenai/pixmo-count) (fine-tuning): diverse images with counting QA pairs
All datasets were constructed **without the use of VLMs**.
<div align="center">
<img src="assets/png_version_molmo_pixmo.png" alt="Pixmo and Molmo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
<br>
<p>Datasets in PixMo (left) and the capabilities they enable in Molmo (right).
<br>
</div>
- [2024/09/24] **🔥 [Molmo](https://huggingface.co/collections/allenai/molmo-66f379e6fe3b8ef090a8ca19)**, a new family of open VLMs, has been released. The Molmo family consists of:
- [**MolmoE-1B**](https://huggingface.co/allenai/MolmoE-1Excerpt of 15,974 characters
Read on GitHub
10
3
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:bf96c29c482c7505, desc:vision-language, desc:vision language model