11 7 27

Thomas Thoresen

thomasht86

https://thomasht86.github.io/

thomasht86

AI & ML interests

None yet

Recent Activity

new activity 4 days ago

vespa-engine/colpali-vespa-visual-retrieval:Update README.md

published a Space 4 days ago

vespa-engine/colpali-vespa-visual-retrieval

updated a Space 4 days ago

vespa-engine/colpali-vespa-visual-retrieval

View all activity

Organizations

New activity in vespa-engine/colpali-vespa-visual-retrieval 4 days ago

Update README.md

#1 opened 4 days ago by

abhishek

published a Space 4 days ago

ColPali 🤝 Vespa - Visual Retrieval

👀

Visual Retrieval with ColPali and Vespa

updated a Space 4 days ago

ColPali 🤝 Vespa - Visual Retrieval

👀

Visual Retrieval with ColPali and Vespa

liked a model 16 days ago

KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5

Feature Extraction • 0.5B • Updated 5 days ago • 7.88k • 39

updated a model 16 days ago

thomasht86/KaLM-embedding-multilingual-mini-instruct-v2.5-ONNX

Feature Extraction • Updated 16 days ago • 13 • 1

published a model 16 days ago

thomasht86/KaLM-embedding-multilingual-mini-instruct-v2.5-ONNX

Feature Extraction • Updated 16 days ago • 13 • 1

commented on ModernVBERT: Towards Smaller Visual Document Retrievers 20 days ago

Thanks - will give it a go!

New activity in vespa-engine/colbert-medium 27 days ago

Adding `safetensors` variant of this model

#2 opened about 1 month ago by

SFconvertbot

commented on ModernVBERT: Towards Smaller Visual Document Retrievers about 1 month ago

Yes, merged model would simplify!
Thank you for the awesome work :)

upvoted an article about 1 month ago

Article

Introducing RTEB: A New Standard for Retrieval Evaluation

Oct 1

• 122

liked a model about 1 month ago

ModernVBERT/colmodernvbert

Visual Document Retrieval • Updated Oct 2 • 6.37k • 23

reacted to Xenova's post with 👍 about 1 month ago

Post

4393

The next generation of AI-powered websites is going to be WILD! 🤯

In-browser tool calling & MCP is finally here, allowing LLMs to interact with websites programmatically.

To show what's possible, I built a demo using Liquid AI's new LFM2 model, powered by 🤗 Transformers.js: LiquidAI/LFM2-WebGPU

As always, the demo is open source (which you can find under the "Files" tab), so I'm excited to see how the community builds upon this! 🚀

2 replies

commented on ModernVBERT: Towards Smaller Visual Document Retrievers about 1 month ago

Fantastic work!
What are the steps required to export an ONNX-model for this?
Same as ColPali?
Created merged model -> Convert to HF weights -> Export?
Would love to help make this happen with some guidance. It would greatly increase adoption imho.