It does this by giving a “likelihood” number to each token. So, for the phrase “I like to bake …”, “cookies” has a higher likelihood than “chairs.” “chairs” can still appear, but “cookies” has a much higher chance. But we can change this behavior with those 3 parameters.
RESEARCH
-
Adjusting Model Parameters: Temperature, Top-k, Top-p
By
–
So, how can you do this? By adjusting the model parameters. There are 3 parameters you can adjust:
1. Temperature
2. Top-k
3. Top-p But before we see how to use them, let’s first understand how the model selects the next token to generate. -
Harmonai joins Replicate with open source audio ML models
By
–
Also, welcome @harmonai_org to Replicate! They're a open source collective of audio ML hackers. This is just the first of many models they're working on and we're looking forward to all those robo-tunes.
-
Fashion-MNIST: 28×28 Single Channel Image Dataset Overview
By
–
fashion-MNIST images are 28×28 single channel.
-
IBM Research Explores Deep Learning Methods to Reduce AI Bias
By
–
#AI bias is more than just unfair – it can amplify social inequalities and create distrust in technology. Using #deeplearning, @IBMResearch are exploring ways to reduce this bias in large pre-trained AI models: https://
ibm.co/3BxXObP -
ImageWoof vs Fashion-MNIST: Neural Network Architecture Considerations
By
–
ImageWoof is much harder, and uses proper RGB images of a useful size! fashion-MNIST is interesting though exactly because they're not normal photographic images. So you gotta think about that carefully when creating your architecture.
-
Privacy in AI: Beyond Training and Model Usage
By
–
And finally, privacy is… hard! While a lot of work focuses on training and using models privately, this is a narrow view of privacy, which encapsulates much more. 14/n
-
Private ML Benchmarks and Privacy-Focused Evaluation Standards
By
–
The second is to re-focus towards benchmarks that are more appropriate for private ML. We now understand that public data can help for private CIFAR-10 and ImageNet classification, which is great. But maybe we should move towards settings where privacy is more important. 13/n
-
Privacy-Respecting Public Pre-Training Datasets for AI Models
By
–
So where do we go from here? We conclude with a number of suggestions for the field. The first ones focuses on making sure we have public pre-training sets which are truly privacy-respecting. Can we make such a dataset/model with comparable utility to what people use now? 12/n
-
FHE Limitations for Large Model Inference Privacy
By
–
But FHE is not so practical for these models. And it may be infeasible to use some of these large models on a user's device. So even with private fine-tuning, then privacy at inference time still remains. 11/n