Some considerations:
It works surprisingly well, not many changes needed besides, of course, the different way @ollama inference works. I just had to add some more info in the prompt for the orchestrator because Llama 3 loves to yap, lol. At one point, it forgot the goal and
@skirano
-
Ollama Integration with Llama 3 Orchestration Works Well
By
–
-
Maestro-Ollama: Local Llama 3 70B Agent Framework
By
–
Introducing Maestro-Ollama! 🦙
— Pietro Schirano (@skirano) 18 avril 2024
You can now harness the power of the Maestro framework entirely locally using Llama 3 70B via @ollama.
Let that sink in for a second, this is a model that outperforms Claude 3 Sonnet, operating as an agent, completely locally.
What a time! 🔥 pic.twitter.com/aC34Bd6F65Introducing Maestro-Ollama! You can now harness the power of the Maestro framework entirely locally using Llama 3 70B via @ollama
. Let that sink in for a second, this is a model that outperforms Claude 3 Sonnet, operating as an agent, completely locally. What a time! -
Context Size Impact on Model Intelligence and Hallucinations
By
–
I thought the same too. I wonder what’s the rationale. I remember reading once that smaller context models tend to be smarter and hallucinate less, but I can't find the source rn. I wonder if it is related to that and if that's something that should be included in evals as well.
-
SD3 Streamlit App for Simultaneous Image Generation
By
–
I wanted everyone to experience the magic of SD3, so I created this little Streamlit app that you can run on @Replit or via the repo. ✨
— Pietro Schirano (@skirano) 17 avril 2024
It generates an image using SD3 and SD3 Turbo simultaneously and supports image-to-image as well.
Just add your API key.
Have fun! 😌 pic.twitter.com/67kTCS7kxXI wanted everyone to experience the magic of SD3, so I created this little Streamlit app that you can run on @Replit or via the repo. It generates an image using SD3 and SD3 Turbo simultaneously and supports image-to-image as well. Just add your API key. Have fun!
-
SD3 Streamlit Implementation Repository Released
By
–
Github https://
github.com/Doriandarko/sd
3-streamlit
… -
SD3 Image Generation: Major Improvements in Composition and Text
By
–
Some first impressions using SD3: – Big step up in composition and notorious issues like hands, "AI faces" etc.
– Seems to prefer simpler prompts.
– Way more copyright-friendly. It's hard to get any kind of brands/logos.
– Text is amazing. Incredible news for @everartai
. -
Stability API Documentation Download Feature for LLM Implementation
By
–
I love how the new Stability API page has a button to download the entire specification. Easiest way to feed it to an LLM for quick implementation and testing. Every documentation page should have this.
-
EverArtAI: Generate Custom AI Models from Instagram Photos
By
–
We just use a few pics from their Instagram account and use "Object" as the training type. @everartai will do all the complicated things for you in the background to make sure you get the best model. As long as you use more than 10 pics, you will get this kind of quality.
-
Models and techniques will continue to improve over time
By
–
, that's exactly the rationale. And to be fair, these models and techniques are only going to improve over time.
-
AI-Generated Assets Nearly Match Real Product Quality at 99%
By
–
I would say that is as close as you can get to the real product with general AI. (99%) Also, each asset has a gradient of application; some of them are perfect for social campaigns, while others are designed for prints, etc. And you could fix that last 1% pretty easily. But you