We tested popular models like GPT-4, Claude, Llama, and Yi using different prompting and decoding techniques to see how much they impact performance for things like: – Question classification
– Sentiment analysis
– Nested JSON schema correctness
MACHINE LEARNING
-
Testing LLM Performance with Prompting and Decoding Techniques
By
–
-
Prompt Engineering Strategies Impact on Llama Model Performance
By
–
We also explored different prompting strategies using a 32B Llama model to see how they impact output performance. For this task (and model), simple, static strategies didn’t work that well in isolation!
-
3 GPTs, including Master AI, boost ChatGPT with autonomous agents
By
–
These 3 #GPTs take #ChatGPT to the next level → https:// youtu.be/yYj4Yz9tJRs Just the first one: Master AI It allows you to create a team of autonomous AI agents to carry out any action!
-
MTEB Evaluation for Bedrock and Vertex Embeddings
By
–
Has anyone done an MTEB eval for bedrock or vertex embeddings?
-
Processing Hundreds of GB Data Cloud Polars
By
–
Process Hundreds of GB of Data in the Cloud with Polars https://
bit.ly/3N2ZnUC
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
3D LiDAR Visualization for Self-Driving Autonomy
By
–
🚀Blog-tastic Tuesdays🚀https://t.co/axILFYgdGu
— Satya Mallick (@LearnOpenCV) 5 décembre 2023
In this definitive research article, we will comprehensively focus on visualizing 3D LiDAR sensor data and try to gain an in-depth understanding of the 3D point cloud representation system for self-driving autonomy.#learnopencv… pic.twitter.com/VGqgUFiD8EBlog-tastic Tuesdays https://
learnopencv.com/3d-lidar-visua
lization/
… In this definitive research article, we will comprehensively focus on visualizing 3D LiDAR sensor data and try to gain an in-depth understanding of the 3D point cloud representation system for self-driving autonomy. #learnopencv -
Condensing Token Embeddings into Single Vectors for Compute Efficiency
By
–
oh yes I've been thinking about some similar things. so you want to condense sequences of token embeddings into a single vector to save compute. I think my research shows this should work in theory (you can condense lots of text into a vector without losing information)
-
Numba Adds Polynomial Support for Machine Learning
By
–
Adding support for polynomials to Numba https://
bit.ly/3N0MZog
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
DensePose and HR-VITON Implementation Guide for Image Synthesis
By
–
This has details on how to run DensePose with what looks like the same styled outputs: https://
github.com/sangyun884/HR-
VITON/issues/45
… cc @FluorescentGrey -
Flash Attention: Why Did Breakthrough Technology Take Years?
By
–
if that were true we would have gotten flash attention years earlier