GitHub – coatless-quarto/r-shinylive-demo: Deploying an R Shiny Application in Quarto with Shinylive (No Shiny Server Required) https://
bit.ly/3SdBHk6 #AI #MachineLearning #DeepLearning #LLMs #DataScience
CODE
-
Deploying R Shiny Applications in Quarto with Shinylive
By
–
-
SDXL ControlNets landscape fragmentation guide
By
–
What are your go to SDXL controlnets? The landscape is a lot more fractured than with SD1.5.
-
SDXL Multi-ControlNet Model with LoRA Support Released
By
–
I've put together a new Replicate SDXL model, it does a lot: – up to 3 controlnets (+ strength, start, end controls)
– controlnet with inpainting/img2img
– canny, QR monster, pose, soft edge, depth, line art
– lora loading https://
replicate.com/fofr/sdxl-mult
i-controlnet-lora
… Please give it a spin -
GPT Studio Launches Custom GPT Development and Promotion Services
By
–
If you're interested in creating a Custom GPT and have a budget but are unsure where to start, I'm launching a GPT studio to help develop GPTs and provide promotional support. Fill out this form if you're interested:
-
Protecting Your AI Instructions From Copy Methods
By
–
Lastly, @borriss shares a method to protect your instructions so others can't just copy your work. It works all of the time most of the time.
-
Distillation: A Powerful Neural Networks Technique
By
–
Distillation is one of the greatest tricks in the neural networks toolbox. https://t.co/VJPPTkWbq9
— Nando de Freitas (@NandoDF) 15 novembre 2023Distillation is one of the greatest tricks in the neural networks toolbox.
-
ChatGPT Built on PyTorch Framework from Meta-FAIR
By
–
ChatGPT is built with PyTorch, which originally developed at Meta-FAIR.
-
Ghostbuster: State-of-the-art LLM-generated Text Detection Method
By
–
New from @BerkeleyNLP
: We’re introducing Ghostbuster, a state-of-the-art method for detecting LLM-generated text. Paper: http://
arxiv.org/abs/2305.15047
Model: http://
ghostbuster.app
Blog: -
Yi-34B Model Llama Compatibility PR Discussion
By
–
BTW Eric did you see the response from their team here saying that if you do a PR with the change then they'll update it to be llama-compatible? https://
huggingface.co/01-ai/Yi-34B/d
iscussions/11
… -
Training AI Model with Basic Repetition Task Testing
By
–
We should try to train it to do something really basic, like repeat 1,2,3,4…10,1,2,3… over and over. That way we can see if it seems to be working correctly after making changes.