7 56 27

Frank Sommers PRO

fsommers

fsommers

AI & ML interests

None yet

Recent Activity

upvoted a paper about 18 hours ago

Scalable Vision Language Model Training via High Quality Data Curation

upvoted a paper about 18 hours ago

Qwen2.5-VL Technical Report

liked a model 2 days ago

vidore/colqwen2.5-v0.2

View all activity

Organizations

fsommers's activity

upvoted 2 papers about 18 hours ago

Scalable Vision Language Model Training via High Quality Data Curation

Paper • 2501.05952 • Published Jan 10 • 1

Qwen2.5-VL Technical Report

Paper • 2502.13923 • Published 2 days ago • 128

liked a model 2 days ago

vidore/colqwen2.5-v0.2

Visual Document Retrieval • Updated about 15 hours ago • 843 • 4

New activity in vidore/colqwen2.5-v0.2 2 days ago

Serverless API

#1 opened 17 days ago by

alexanderniebuhr

upvoted a collection 2 days ago

ColQwen2 Models

Collection

Pre-trained checkpoints for the ColQwen2 model. • 4 items • Updated 29 days ago • 2

upvoted a collection 6 days ago

Qwen2.5-VL

Collection

Vision-language model series based on Qwen2.5 • 3 items • Updated 26 days ago • 359

upvoted an article 7 days ago

Article

We now support VLMs in smolagents!

29 days ago

• 84

reacted to burtenshaw's post with ❤️ 13 days ago

Post

3497

SmolLM2 paper is out! 😊

😍 Why do I love it? Because it facilitates teaching and learning!

Over the past few months I've engaged with (no joke) thousands of students based on SmolLM.

- People have inferred, fine-tuned, aligned, and evaluated this smol model.
- People used they're own machines and they've used free tools like colab, kaggle, and spaces.
- People tackled use cases in their job, for fun, in their own language, and with their friends.

upvote the paper SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model (2502.02737)