Hugging Face's logo
Victor Sanh's picture
183 55 160

Victor Sanh PRO

VictorSanh
ybelkada's profile picture itboos's profile picture ericksnetwork's profile picture
·
SanhEstPasMoi
VictorSanh

AI & ML interests

None yet

Articles

Organizations

Hugging Face's profile picture BigScience Workshop's profile picture Big Science - Modeling Metadata's profile picture HuggingFaceM4's profile picture BigCode's profile picture Benchmark Cluster's profile picture Hugging Face H4's profile picture Hugging Face Smol Cluster's profile picture Hugging Face TB Research's profile picture ZeroGPU Explorers's profile picture Pixel Parsing's profile picture Hugging Face Assignments's profile picture Social Post Explorers's profile picture DistilBERT community's profile picture Hacks/Hackers AI hackathon at Brown Center's profile picture

Posts 6

view post
Post
2015
Glad to see Idefics2 making its way into the awesome OpenVLM Leaderboard which ranks VLMs. 🏆
2nd in its category (<10B parameters and open weights)!

While InternLM-XComposer2 uses proprietary data, Idefics2 is built solely using openly available data.

Leaderboard: opencompass/open_vlm_leaderboard
Model: HuggingFaceM4/idefics2-8b
view post
Post
2464
Can't wait to see multimodal LLama 3!

We released a resource that might come in handy: The Cauldron 🍯

The Cauldron is a massive manually-curated collection of 50 vision-language sets for instruction fine-tuning. 3.6M images, 30.3M query/answer pairs.

It covers a large variety of downstream uses: visual question answering on natural images, OCR, document/charts/figures/tables understanding, textbooks/academic question, reasoning, captioning, spotting differences between 2 images, and screenshot-to-code.

HuggingFaceM4/the_cauldron
View all posts

Collections 1

Papers 15