Stability AI announced the release of Stable Video Diffusion, marking a huge leap forward for open source novel video synthesis
Building on top of open source models gives you access to a wide range of capabilities that you would otherwise lack from a black box endpoint provider.
Switching from a closed source ecosystem where you consume ML models from API endpoints to the world of open source ML models can seem intimidating. But this checklist will give you all of the resources you need to make the leap.
When you depend on an open source package, like transformers from PyPi, the best practice is to pin the version you use to ensure there aren’t breaking changes or security vulnerabilities introduced to your codebase. You can do the same for model weights and associated code by pinning a model revision.
A text embedding model transforms text into a vector of numbers that represents the text’s semantic meaning. There are a number of high-quality open source text embedding models for different use cases across search, recommendation, classification, and retrieval-augmented generation with LLMs.
Jina AI released jina-embeddings-v2-base-en, a text embedding model that matches OpenAI’s ada-002 model in both benchmark performance and context window length.
AudioGen, part of the AudioCraft family of models from Meta AI, is now available in the Baseten model library.
Deploy Stable Diffusion XL 1.0 for free to generate images from text prompts and invoke Stable Diffusion with the Baseten Python client.
An in-depth look at open source foundation models, both LLMs and image models: Llama 2 from Meta and Microsoft, FreeWilly1 and FreeWilly2 from Stability AI, SDXL 1.0 (Stable Diffusion XL) also from Stability AI, LayoutLM Document QA from Inspira, and NSQL 350M from Number Station.
Deploy Falcon-40B and Falcon-7B, top-ranked open-source LLMs on HuggingFace, to Baseten's production-ready ML infrastructure.