Anyone know why @StabilityAI
's Stability SDK Python lib generates massive 3.5 GB folders full of ProtoBuffer *.pb files?
CODE
-
Stability SDK Python generates massive 3.5 GB ProtoBuffer files
By
–
-

Favorite Use Case Demonstration with Perplexity AI SQL
By
–
This is actually one of my favorite use cases. https://
perplexity.ai/sql?uuid=a2528
57b-284f-45a2-a7bc-3a797db17188
… -

Docker Now Available for Spaces: Deploy ML Apps Easily
By
–
You can now run Docker with Spaces! What does that mean? @elixirlang Phoenix, Dash, FastAPI, Shiny, and your favorite ML tools can now be used with Spaces! What will you build?
-

Learning Recommendation Systems with Movie Dataset
By
–
Recommendation systems are one of the most widely used topics of machine learning. Some of your favorite applications use a recommendation system at their core. Here is a great dataset to learn: https://
kaggle.com/rounakbanik/th
e-movies-dataset
… 45,000+ movies. 26M ratings from over 270,000 users. -

Automate Text Analysis with IBM Watson NLP Library
By
–
Reading through endless amounts of comments about your business can get tiring With #IBMWatson's #NLP Library, automatically gather, process and classify large datasets of text by emotion. Learn how here: https://
ibm.co/3BwoDgn via @IBMDeveloper —–
#LearningPath #AI -
Machine Learning Project: Detecting Outliers in Sensor Data
By
–
Full Machine Learning Project — Detecting Outliers in Sensor Data (Part 4) #DataScience
-
Tokenizer Libraries Essential Features for NLP Tasks
By
–
it's not really doing the same thing, they are doing encoding only while the tokenizer lib does a lot of work keeping track of offset between the original string and the final tokens, truncating, etc. this is needed to support various model hub task like QA, etc
-

Fast BPE Tokenizer Open-Sourced for Language Models
By
–
Just open-sourced our screaming-fast BPE tokenizer:
-
Model Fine-tuning Across Multiple Genres Discussion
By
–
I think it's only finetuned on some diff genres
-
Constraints Force Focus on Essential Features Over Overengineering
By
–
Excuses imho. Constraints are very helpful. Makes you focus on the bare minimum important. Everyone overengineers.