Building RAG Pipelines that Use Multiple LLMs: Query Transformation Many advanced RAG pipelines make multiple calls to LLMs at various stages. Most existing templates currently use the same LLM for all stages, but there's no reason that has to be the case. Over the coming
GENERATIVE AI
-
LVM Revolution: How Vision Models Differ from Language Models
By
–
The LVM (large vision model) revolution is coming a little after the LLM (large language model) one, and will transform how we process images. But there’s an important difference between LVMs and LLMs:
— Andrew Ng (@AndrewYNg) 4 décembre 2023
– Internet text is similar enough to proprietary text documents that an LLM… pic.twitter.com/PzyXpGbQiCThe LVM (large vision model) revolution is coming a little after the LLM (large language model) one, and will transform how we process images. But there’s an important difference between LVMs and LLMs:
– Internet text is similar enough to proprietary text documents that an LLM -
MusicGen Fine-tune Creates Festive Christmas Bells with Runway Video
By
–
I enjoyed putting this one together. The MusicGen fine-tune is one of my favourites – lots of xmas bells, very festive.
— fofr (@fofrAI) 4 décembre 2023
The video is an image to video using Runway, and an overlaid waveform. Original image by dalle3. https://t.co/t1rKLeU086I enjoyed putting this one together. The MusicGen fine-tune is one of my favourites – lots of xmas bells, very festive. The video is an image to video using Runway, and an overlaid waveform. Original image by dalle3.
-
Magnific AI Image Upscaling Tool Produces Gorgeous Results
By
–
And that image looks simply gorgeous when upscaled with Magnific.
-
MLOps Community LLMs Mini Summit Meetup Event
By
–
MLOps Community: LLMs Mini Summit // MLOps Mini Summit Meetup #3 https://
bit.ly/3N2oEyx
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
MusicGen Christmas: Generate Holiday Music with AI
By
–
Is that sleigh bells?
— Replicate (@replicate) 4 décembre 2023
🔊 https://t.co/kQm8inuKSe pic.twitter.com/p7tG3DHxikIs that sleigh bells? https://
replicate.com/fofr/musicgen-
xmas
… -
Achieving Human-Level AI: SSL, World Models, and Planning Approaches
By
–
For the record: I was never a skeptic.
I always said that human level AI was achievable within decades.
I also said it was harder than what most people thought & was not "just around the corner."
I said we weren't going to get to it with RL.
I said SSL, world models, and planning -
Multimodal Vision Support Transforms LangSmith Playground
By
–
🌌 🛝 Multimodal support in LangSmith Playground
— LangChain (@LangChain) 4 décembre 2023
With the announcement of GPT-4-vision models, it has never been easier to convert rough sketches into runnable prototypes.
Nevertheless, a simple prompt may not suffice, and prompt engineering can guide the LLM to yield better… pic.twitter.com/55NnFHbg8eMultimodal support in LangSmith Playground With the announcement of GPT-4-vision models, it has never been easier to convert rough sketches into runnable prototypes. Nevertheless, a simple prompt may not suffice, and prompt engineering can guide the LLM to yield better
-
Gen-2: Advanced Text-to-Video AI Model by Runway
By
–
Turn words into worlds with the most advanced text to video AI model: Gen-2
— Runway (@runwayml) 4 décembre 2023
Any story. Every style. Completely generated.https://t.co/ekldoIshdw pic.twitter.com/q1xK84hpd1Turn words into worlds with the most advanced text to video AI model: Gen-2 Any story. Every style. Completely generated. http://
runwayml.com