that feeling when you finally understand a piece of previously inscrutable code
SOFTWARE
-
Placeholder Syntax Reliability and Tokenization Issues in GPT Models
By
–
I haven’t tried it but agree {placeholder} syntax is pretty reliable in practice for GPT-3.5 and up; more generally you do see issues I suspect are tokenization related. E.g. 4 can struggle to notice ““python” (for a Markdown code block) is missing a backtick.
-
Keras with JAX outperforms PyTorch in speed benchmarks
By
–
I don't know about tinygrad. But Keras with JAX is typically 30% faster than PyTorch, sometimes more. Our SegmentAnything implementation is 5x faster than the original PyTorch version.
-
NumPy optimization framework supporting multiple deep learning backends
By
–
You can think of it as an optimized & extended NumPy that compiles to any of JAX, TF, PyTorch, or… NumPy itself.
-
Keras 3 Introduces Low-Level API Supporting JAX TensorFlow PyTorch
By
–
Keras 3 features a low-level `keras.ops` API with 201 functions that work in JAX, TensorFlow, and PyTorch with the exact same semantics and numerics. This includes 137 NumPy ops. It's not "numpy-like", it's literally the NumPy API (plus a bunch of NN ops).
-
Flowise 1.4.3 Patch Release: Updates and Improvements
By
–
Patch note https://
github.com/FlowiseAI/Flow
ise/releases/tag/flowise1.4.3
… Thanks to all contributors -
Flowise Chatflow UI/UX Enhancement with List View
By
–
🪄 Chatflow UI/UX
— FlowiseAI (@FlowiseAI) 24 novembre 2023
We've enhanced the UI/UX of Flowise Chatflow view, enabling list view for easier management of your chatflows, and tagging as well. pic.twitter.com/g4zMY8xCjEChatflow UI/UX We've enhanced the UI/UX of Flowise Chatflow view, enabling list view for easier management of your chatflows, and tagging as well.
-
MongoDB Atlas Vector Store Integration with Flowise Now Available
By
–
MongoDB Atlas @MongoDB Atlas Vector Store and Memory are both supported on Flowise!
-
Flowise v1.4.3 Release: New APIs, Claude 2.1 and MongoDB Support
By
–
Friday release time
Flowise v1.4.3 freshly baked with: Upsert API Moderation Claude 2.1 support Langfuse User Tracing Vectara QA Chain MongoDB Atlas Chatflow UI/UX -
Python UDTFs in Apache Spark 3.5 and Databricks Runtime
By
–
#ApacheSpark 3.5 and Databricks Runtime 14.0 have brought an exciting feature to the table: Python UDTFs This new feature can generate multiple rows and columns, while leveraging the rich Python ecosystem. Learn how it works