SAM 2: Segment Anything Model - A new open-source model that can segment any promptable objects from images or videos in real-time. ??
Welcome to the?AI in 5?newsletter with Clarifai!
Every week we bring you new models, tools, and tips to build production-ready AI!
Here is the summary of what we will be covering this week: ??
SAM-2(Segment Anything Model) from Meta??
Meta AI released the new open-source SAM 2 (Segment Anything Model) that can segment any promptable objects from images or videos in real time.
SAM 2 outperforms previous approaches on interactive video segmentation across 17 zero-shot video datasets and is 6x faster than SAM.
The model is trained on SA-V Dataset which is 4.5 times larger than existing datasets and contains approximately 53 times more annotations than the largest current video segmentation dataset.
Mistral 12B Nemo Instruct ??
Mistral NeMo is the new and the best small model from Mistral AI built in collaboration with NVIDIA. This is a state-of-the-art 12B model with a 128k context length.?
The model offers a balance between size and performance, offering advanced capabilities on a manageable scale.
The model also excels in reasoning, world knowledge, and coding tasks, making it one of the most capable models within its size category.?
The Instruct variant is now available on the Clarifai Platform. Try out the model here!
Build RAG apps with EmbedChain ??
Clarifai is now integrated with EmbedChain AI!
EmbedChain is an open-source framework designed to streamline the integration of LLMs with custom knowledge bases.
With this integration, you can now leverage the LLMs and embedding models from the Clarifai Platform to build RAG applications.
Check out the below RAG tutorial to get started.
领英推荐
Webinar Recording: AI Prototype to Production
Last week, we hosted a webinar on operationalizing and orchestrating AI.
If you missed it, don’t worry! Get the recording below and learn more about the best practices to move your AI projects from prototype to production faster.
Get the recording here.
Access Text to Audio Models using an API
The Text to Audio?models, powered by our Predict API, seamlessly transform provided textual content into an audio file using advanced speech synthesis models.?
This capability allows you to effortlessly convert written text into a natural and expressive audio experience.
There are models available from Open AI, Deepgram and Elevenlabs. Check out the guide here on how to access these models.
Tip of the week: ??
App Templates?
Create applications faster with pre-built blueprints.
Clarifai app templates are pre-built blueprints that provide a starting point for creating your applications.?
When you choose a template to create an app, the configurations and resources available in the template will be preemptively applied to your new application. You can use the pre-built components to quickly apply AI to your specific use case.
Check out the App Templates here.
Want to learn more from Clarifai? “Subscribe” to make sure you don’t miss the latest news, tutorials, educational materials, and tips. Thanks for reading!