Frank Sommers PRO

fsommers's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection about 12 hours ago

Gemma 3 Release

Collection

9 items • Updated about 14 hours ago • 229

upvoted a paper 7 days ago

NitiBench: A Comprehensive Studies of LLM Frameworks Capabilities for Thai Legal Question Answering

Paper • 2502.10868 • Published 27 days ago • 2

updated a collection 10 days ago

Misc papers

Collection

14 items • Updated 10 days ago

upvoted a paper 10 days ago

ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents

Paper • 2502.18017 • Published 17 days ago • 18

upvoted 2 articles 14 days ago

view article

Article

SmolVLM2: Bringing Video Understanding to Every Device

22 days ago

• 205

view article

Article

SigLIP 2: A better multilingual vision language encoder

21 days ago

• 134

upvoted a paper 15 days ago

Executable Code Actions Elicit Better LLM Agents

Paper • 2402.01030 • Published Feb 1, 2024 • 97

upvoted 2 papers 21 days 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 23 days ago • 164

liked a model 23 days ago

vidore/colqwen2.5-v0.2

Visual Document Retrieval • Updated 21 days ago • 7.43k • 10

New activity in vidore/colqwen2.5-v0.2 23 days ago

Serverless API

1

#1 opened about 1 month ago by

alexanderniebuhr

upvoted a collection 23 days ago

ColQwen2 Models

Collection

Pre-trained checkpoints for the ColQwen2 model. • 4 items • Updated Jan 23 • 4

upvoted a collection 26 days ago

Qwen2.5-VL

Collection

Vision-language model series based on Qwen2.5 • 8 items • Updated 18 days ago • 397

upvoted an article 27 days ago

view article

Article

We now support VLMs in smolagents!

Jan 24

• 92

reacted to burtenshaw's post with ❤️ about 1 month ago

view post

Post

3704

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)

See translation

• 
• 1 reply

·

❤️

8

8

🤗

3

3

👍

2

2

🚀

1

1

+

Reply

upvoted a paper about 1 month ago

ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning

Paper • 2502.01100 • Published Feb 3 • 17

liked a Space about 1 month ago

Running on Zero

55

55

GOT OCR Transformers

📷

Demo of GOT-OCR 2.0's Transformers implementation

upvoted an article about 1 month ago

view article

Article

Visualize and understand GPU memory in PyTorch

Dec 24, 2024

• 195

liked a Space about 2 months ago

Running

150

150

Qwen2.5 VL 72B Instruct

💻

Interact with Qwen2.5-VL-Chat model using text and files

liked a model about 2 months ago

Qwen/Qwen2.5-VL-7B-Instruct

Image-Text-to-Text • Updated 8 days ago • 3.39M • • 666