217 61 184

Victor Sanh PRO

VictorSanh

AI & ML interests

None yet

Recent Activity

New activity about 2 months ago

shuaishuaicdp/GUI-World:keyframes in `android.jsonl`?

liked a dataset about 2 months ago

agent-studio/GroundUI-18K

View all activity

Articles

Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

Apr 15

• 166

Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset

Mar 15

• 6

Introducing IDEFICS: An Open Reproduction of State-of-the-art Visual Language Model

Aug 22, 2023

• 27

Organizations

Posts 7

Post

2762

💬🔥Releasing idefics2-8b-chatty, the chat-optimized version of Idefics2!

It is a very efficient (8B parameters) state-of-the-art VLM, has been red-teamed, and comes with a few surprises:
- 📖Paper dissecting a lot of the experimental insights we learned building Idefics2:
- 🏎️TGI integration for blazing-fast inference (you can already run it locally with < 24GB GPU memory)
- 🏆 Ranking 2nd in its category (< 10B, open weights) in the awesome Open VLM Leaderboard, and now appearing in the incredible Vision Arena

Ressources:
⏯️Playground: HuggingFaceM4/idefics2_playground
📖Paper: What matters when building vision-language models? (2405.02246)
🏋️‍♂️Model and red-teaming analysis: HuggingFaceM4/idefics2-8b-chatty
👀Ressources to get started: HuggingFaceM4/idefics2-8b-chatty
🏆Open VLM Leaderboard: opencompass/open_vlm_leaderboard
🏟️Vision arena: WildVision/vision-arena

Post

2722

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 all posts