EmbeddingGemma: Powerful and Lightweight Text Representations
Paper
•
2509.20354
•
Published
•
43
AI & ML interests
Open science and open source
Recent Activity
View all activity
osanseviero
authored
a
paper
4 months ago
freddyaboulton
posted
an
update
4 months ago
Post
2159
Gradio 6.0 is launching this year!
We're revamping the core to give you performance improvements and unprecedented customization. Build better, faster.
Check out the GitHub milestone to learn what's planned under the hood!
https://github.com/gradio-app/gradio/issues?q=is:issue%20state:open%20milestone:%22Gradio%206%22
We're revamping the core to give you performance improvements and unprecedented customization. Build better, faster.
Check out the GitHub milestone to learn what's planned under the hood!
https://github.com/gradio-app/gradio/issues?q=is:issue%20state:open%20milestone:%22Gradio%206%22
rootacess
authored
a
paper
6 months ago
freddyaboulton
posted
an
update
7 months ago
freddyaboulton
posted
an
update
7 months ago
Post
770
Time is running out! ⏰
Less than 24 hours to participate in the MCP Hackathon and win thousands of dollars in prizes! Don't miss this opportunity to showcase your skills.
Visit Agents-MCP-Hackathon/AI-Marketing-Content-Creator to register!
Less than 24 hours to participate in the MCP Hackathon and win thousands of dollars in prizes! Don't miss this opportunity to showcase your skills.
Visit Agents-MCP-Hackathon/AI-Marketing-Content-Creator to register!
freddyaboulton
posted
an
update
7 months ago
Post
563
🚨 NotebookLM Dethroned?! 🚨
Meet Fluxions vui: The new open-source dialogue generation model.
🤯 100M Params, 40k hours audio!
🎙️ Multi-speaker audio
😂 Non-speech sounds (like [laughs]!)
📜 MIT License
Is this the future of content creation? Watch the video and decide for yourself!
https://huggingface.co/spaces/fluxions/vui-spacehttps://huggingface.co/fluxions/vui
Meet Fluxions vui: The new open-source dialogue generation model.
🤯 100M Params, 40k hours audio!
🎙️ Multi-speaker audio
😂 Non-speech sounds (like [laughs]!)
📜 MIT License
Is this the future of content creation? Watch the video and decide for yourself!
https://huggingface.co/spaces/fluxions/vui-spacehttps://huggingface.co/fluxions/vui
- 1 reply
ethanhe
authored
a
paper
9 months ago
osanseviero
authored
a
paper
10 months ago
freddyaboulton
posted
an
update
10 months ago
Post
2258
Ever wanted to share your AI creations with friends? ✨
Screenshots are fine, but imagine letting others play with your ACTUAL model!
Introducing Gradio deep links 🔗 - now you can share interactive AI apps, not just images.
Add a gr.DeepLinkButton to any app and get shareable URLs that let ANYONE experiment with your models.
Screenshots are fine, but imagine letting others play with your ACTUAL model!
Introducing Gradio deep links 🔗 - now you can share interactive AI apps, not just images.
Add a gr.DeepLinkButton to any app and get shareable URLs that let ANYONE experiment with your models.
freddyaboulton
posted
an
update
10 months ago
Post
2094
Privacy matters when talking to AI! 🔇
We've just added a microphone mute button to FastRTC in our latest update (v0.0.14). Now you control exactly what your LLM hears.
Plus lots more features in this release! Check them out:
https://github.com/freddyaboulton/fastrtc/releases/tag/0.0.14
We've just added a microphone mute button to FastRTC in our latest update (v0.0.14). Now you control exactly what your LLM hears.
Plus lots more features in this release! Check them out:
https://github.com/freddyaboulton/fastrtc/releases/tag/0.0.14
freddyaboulton
posted
an
update
11 months ago
Post
3413
Getting WebRTC and Websockets right in python is very tricky. If you've tried to wrap an LLM in a real-time audio layer then you know what I'm talking about.
That's where FastRTC comes in! It makes WebRTC and Websocket streams super easy with minimal code and overhead.
Check out our org: hf.co/fastrtc
That's where FastRTC comes in! It makes WebRTC and Websocket streams super easy with minimal code and overhead.
Check out our org: hf.co/fastrtc
Post
1770
New state-of-the-art BERT-size retrieval model: *cde-small-v2* 🥳🍾
Hi everyone! We at Cornell are releasing a new retrieval model this week. It uses the contextual embeddings framework, is based on ModernBERT backbone, and gets state-of-the-art results on the MTEB benchmark for its model size (140M parameters). cde-small-v2 gets an average score of 65.6 across the 56 datasets and sees improvements from our previous model in *every* task domain (retrieval, classification, etc.).
We made a lot of changes to make this model work. First of all, ModernBERT has a better tokenizer, which probably helped this work out-of-the-box. We also followed the principles from the CDE paper and used harder clusters and better hard-negative filtering, which showed a small performance improvement. And we made a few small changes that have been shown to work on the larger models: we disabled weight decay, masked out the prefix tokens during pooling, and added a residual connection from the first-stage to the second-stage for better gradient flow.
We're still looking for a computer sponsor to help us scale CDE to larger models. Since it's now state-of-the-art at the 100M parameter scale, it seems to be a reasonable bet that we could train a state-of-the-art large model if we had the GPUs. If you're interested in helping with this, please reach out!
Here's a link to the model: jxm/cde-small-v2
And here's a link to the paper: Contextual Document Embeddings (2410.02525)
Hi everyone! We at Cornell are releasing a new retrieval model this week. It uses the contextual embeddings framework, is based on ModernBERT backbone, and gets state-of-the-art results on the MTEB benchmark for its model size (140M parameters). cde-small-v2 gets an average score of 65.6 across the 56 datasets and sees improvements from our previous model in *every* task domain (retrieval, classification, etc.).
We made a lot of changes to make this model work. First of all, ModernBERT has a better tokenizer, which probably helped this work out-of-the-box. We also followed the principles from the CDE paper and used harder clusters and better hard-negative filtering, which showed a small performance improvement. And we made a few small changes that have been shown to work on the larger models: we disabled weight decay, masked out the prefix tokens during pooling, and added a residual connection from the first-stage to the second-stage for better gradient flow.
We're still looking for a computer sponsor to help us scale CDE to larger models. Since it's now state-of-the-art at the 100M parameter scale, it seems to be a reasonable bet that we could train a state-of-the-art large model if we had the GPUs. If you're interested in helping with this, please reach out!
Here's a link to the model: jxm/cde-small-v2
And here's a link to the paper: Contextual Document Embeddings (2410.02525)
ethanhe
authored
a
paper
about 1 year ago
freddyaboulton
posted
an
update
about 1 year ago
Post
1890
Just created a Gradio space for playing with the new OAI realtime voice API!
freddyaboulton/openai-realtime-voice
freddyaboulton/openai-realtime-voice
freddyaboulton
posted
an
update
about 1 year ago
Post
1069
Gemini can talk 🗣️
Check out the new multimodal API from Google on @akhaliq 's anychat or my space. It's very fast and smart 🍓
https://huggingface.co/spaces/freddyaboulton/gemini-voicehttps://huggingface.co/spaces/akhaliq/anychat
Check out the new multimodal API from Google on @akhaliq 's anychat or my space. It's very fast and smart 🍓
https://huggingface.co/spaces/freddyaboulton/gemini-voicehttps://huggingface.co/spaces/akhaliq/anychat
-
- 1 reply
freddyaboulton
posted
an
update
about 1 year ago
Post
3190
Version 0.0.21 of gradio-pdf now properly loads chinese characters!
freddyaboulton
posted
an
update
about 1 year ago
Post
1698
Hello Llama 3.2! 🗣️🦙
Build a Siri-like coding assistant that responds to "Hello Llama" in 100 lines of python! All with Gradio, webRTC 😎
freddyaboulton/hey-llama-code-editor
Build a Siri-like coding assistant that responds to "Hello Llama" in 100 lines of python! All with Gradio, webRTC 😎
freddyaboulton/hey-llama-code-editor
freddyaboulton
posted
an
update
about 1 year ago
Post
1241
Just created a cookbook of real time audio/video spaces created using Gradio and WebRTC ⚡️
Use this and the [docs](https://freddyaboulton.github.io/gradio-webrtc/) to get started building the next gen of AI apps!
freddyaboulton/gradio-webrtc-cookbook-6758ba7745aeca7b1be7de0f
Use this and the [docs](https://freddyaboulton.github.io/gradio-webrtc/) to get started building the next gen of AI apps!
freddyaboulton/gradio-webrtc-cookbook-6758ba7745aeca7b1be7de0f
-
- 2 replies
Vishnou
authored
a
paper
about 1 year ago
Post
3594
🏁 Now it is possible to chat with telemetry data from real Formula 1 races!
This is an AI-powered solution for analyzing and generating detailed reports on Formula 1 racing sessions. This project combines the power of ReAct agents from LangChain with a RAG approach to pull data from a SQL database.
At the core of this system is a text-to-SQL capability that allows users to ask natural language questions about various aspects of F1 races, such as driver performance, weather impact, race strategies, and more. The AI agent then queries the database, processes the information, and generates comprehensive reports tailored to the user's needs.
The reports can be exported in various formats, making it easy to share insights with team members, race fans, or the broader motorsports community.
(The project is in beta, some erros may occur)
Check it out:
- Draichi/Formula1-race-debriefing
- https://github.com/Draichi/formula1-AI
This is an AI-powered solution for analyzing and generating detailed reports on Formula 1 racing sessions. This project combines the power of ReAct agents from LangChain with a RAG approach to pull data from a SQL database.
At the core of this system is a text-to-SQL capability that allows users to ask natural language questions about various aspects of F1 races, such as driver performance, weather impact, race strategies, and more. The AI agent then queries the database, processes the information, and generates comprehensive reports tailored to the user's needs.
The reports can be exported in various formats, making it easy to share insights with team members, race fans, or the broader motorsports community.
(The project is in beta, some erros may occur)
Check it out:
- Draichi/Formula1-race-debriefing
- https://github.com/Draichi/formula1-AI
- 1 reply