Toan Ngo Sy

Got my PoK NFT, very cool experience! @jeanlouisguerdy @royalbutcool @simpleojoni @JaviBlvck @re_zzidge @mohandabudamir @mdpsteve @Re40441 @sy_izar @enoch_olagoke

This is quite the paper! It gave 25 AI agents motivations & memory, and put them in a simulated town. Not only did they engage in complex behavior (including throwing a Valentine’s Day party) but the actions were rated more human than humans roleplaying. arxiv.org/pdf/2304.03442…

I am very excited to announce I have been successful in installing and operating a full ChatGPT knowledge set and interface fully trained on my local computer and it needs no Internet once installed. There are no editors and there is no censorship. I am using Alpaca (crfm.stanford.edu/2023/03/13/alp…) from Stanford and Dalai Lama. The training model cost about $530 to build locally yet has the abilities of GPT 3.5. The software is free and open source and I am working on preconfigured packages for anyone to have local training and access to a LLM GPT AI. This model is now in a live connect with all of my other AI systems and the results have been absolutely stunning. I will be writing more about this soon. But today know, you will own your own AI and it will only answer to you.

🛠 New posts on Prompt Engineering: Steer a large pretrained language model to do what you want wo/ updating the model weights. lilianweng.github.io/posts/2023-03-… Most importantly this just introduces general ideas, but for your own problem, you always need tuning and experimentation.

After LLaMA, Alpaca, 22h (@Predogl and I) present you Cabrita. By simply translating the Alpaca dataset to Portuguese, and running LORA training, achieved ChatGPT-like behavior on that language, with only 16mb of LORA weights. huggingface.co/22h/cabrita-lo… 1/n

My friend makes this video using 4 hand-drawn images + #Live3D-v2 + #stablediffusion . Looks like AI assisting anime creation has gone to the next level! (original output from Live3D can be found on github.com/transpchan/Liv…)

20 tests with AI to increase the resolution INSANITY mode. From #pixelart to megadetail with #stablediffusion. Left: "Initial image" VS Right: result "imagined". I will also explain step by step how you can try yourself! Your head will blow up 🤯 1. Super Mario. More 🧵👇

OMG it finally works!! 🚀🚀🚀 I got @OpenAI to draft emails 📧 for me in the background 🤯 This christmas I built an email assistant (EmailTriager.com) that automatically drafts email replies behind the scenes no chrome extension necessary, here's the story 👇

Good news 🎊🌟 I found a way running #stablediffusion #webui inside #Jupyter inside 🤗 @huggingface hehe, just duplicate the jupyter spaces and add gpu 🎉 I put a little surprise folder 🎁🎀 happy holiday🤗🎄🎅 ❤huggingface.co/spaces/camendu…

Godot RL Agents v0.4.0 has been released. 👉github.com/edbeeching/god… This includes: ‣ Godot 4 support ‣ 3 RL frameworks: Sample Factory, Stable Baselines 3 and rllib ‣ 2 Advanced Racing and FPS environments ‣ Updated docs (still WIP🙂) Find out more in this thread 🧵

thanks @diffuserslib team ❤ everything super simple 🤗 Open Source DALL-E 2 from kakaobrain ❤ github.com/kakaobrain/kar… huggingface.co/spaces/kakaobr…

“Stable Diffusion for 3D” is coming Here’s a Text-to-3D point map demo on @huggingface by @hahahahohohe huggingface.co/spaces/anzorq/… “Mid century modern chair” prompt returned this.

Novel highly efficient training framework for reconstructing dynamical systems from *multimodal* data incl. discrete rand. var.: arxiv.org/abs/2212.07892 Clever combi. of MVAE+TF+RNN outperforms everything else we tested. @brenner_manuel will present this at #aaai WS on #MLmDS.

I'm thinking we can do something similar for mesh generation. Mesh can be flattened to 2D image - geometry image hhoppe.com/proj/gim/

I am excited that our paper linking chaos, balance, and learning in recurrent neural networks is now published: journals.plos.org/ploscompbiol/a… We ask: "When can time-varying input suppress chaos and thus control the network state of a balanced rate network?" 1/n

It's awesome to tell people: "Decorate your function with `@stub.function(gpu=A100())` to use a GPU". No kubernetes, no aws, no nvidia drivers. @modal_labs #stablediffusion modal.com/docs/guide/ex/…

geometry-central now supports automatic remeshing, thanks to @MarkGillespie64! Great for quickly improving the density/element quality of surface meshes. It also supports callbacks that get invoked after each mesh operation to implement custom policies. geometry-central.net/surface/algori…

Simple Stable Diffusion to Blender: 1. Use Automatic1111's depth map extension (github.com/thygate/stable…) to create image (img2img or txt2img) & depth map. 2. Import to Blender using Depth Map Importer github.com/AUTOMATIC1111/… 3. That's it - play around! #stablediffusion #aiart