Introducing phi-2-dpo-7k! A Microsoft Phi-2, fine-tuned on a diverse cocktail of 7k chat interactions from @argilla_io
's latest DPO dataset, including orca pairs, ultra-feedback ratings, and capybara-dpo Runs ultra-fast on Apple Silicon, thanks to MLX
GENERATIVE AI
-
Phi-2-DPO-7K: Microsoft’s Fast Fine-Tuned Language Model
By
–
-
Comparing MidJourney DALL-E and Stable Diffusion for Image Generation
By
–
Depends. MidJourney if I want realistic. DALL-e if I want something precise. Stable Diffusion if I want to use controlnets and custom models to really dial something in.
-
Research Advances in Text Embeddings Language Models and Prompting
By
–
a tiny summary of my research projects of 2023: Text Embeddings Reveal (Almost) As Much As Text EMNLP 2023, http://
arxiv.org/abs/2310.06816 Language Model Inversion ICLR 2024, http://
arxiv.org/abs/2311.13647 TreePrompting EMNLP 2023, http://
arxiv.org/abs/2310.14034 -
Can AI-Powered Search Engine Replace Google?
By
–
Can This #AI -Powered Search Engine Replace Google? https://
nytimes.com/2024/02/01/tec
hnology/perplexity-search-ai-google.html
… via @GoogleNews -
Anticipating voice-only AI interaction modes
By
–
A new era! Looking forward to seeing a voice-only mode where you can talk with the cloud (like on mobile apps)
-
AI Containment Essential for Realizing Technology Benefits
By
–
"I believe these technologies can deliver an extraordinary amount of good. But without what I call containment, every other aspect of a technology, every discussion of its ethical shortcomings, or the benefits it could bring, is inconsequential."
-
Siri as Next Major Consumer AI Adoption Milestone
By
–
I still think the next Siri will be the next ChatGPT moment for major consumer AI adoption.
-
Document Search Retrieval RAG Open Source Guide
By
–
Document Search and Retrieval using RAG Great guide by @LightningAI and @aniketmaurya on building a retrieval pipeline Uses open source embedding and reranking models! https://
lightning.ai/lightning-ai/s
tudios/document-search-and-retrieval-using-rag?view=public§ion=recent
… -
Vector Embeddings: Essential for LLM Applications and Real-Time Retrieval
By
–
The popularity of LLMs has made vector embeddings popular and useful. You have to create embeddings for all of your data; whether that is text, speech or a mixture of both. With these embeddings, you also want the ability to retrieve them and send it to an LLM in real time.
-
Guns N’ Roses Music Video with Stable Diffusion AI
By
–
Let’s go for a ride together! 🎶🎸Check out this incredible @gunsnroses music video blending their music with Stable Diffusion. https://t.co/Qn1d7aDV7a
— Stability AI (@StabilityAI) 2 février 2024Let’s go for a ride together! Check out this incredible @gunsnroses music video blending their music with Stable Diffusion.