https://
github.com/hwchase17/noti
on-qa
… one of the first ever demos!
CODE
-
Early Demo of Notion-Based QA AI System
By
–
-
End-to-End ML Platform: Complete Feature Set Overview
By
–
This is what an end-to-end ML platform looks like: • Streaming Pipelines
• Data Wrangling
• Real-Time Feature Store
• SOTA Models
• Notebook Hosting
• Training Pipelines
• Plug & Play Models
• Batch Predictions
• Model Monitoring & Drift Take a look at @abacusai
. -
5 Upcoming Python Libraries You Should Know 2023
By
–
5 Upcoming Python Libraries You Don’t Want to Miss in 2023: This article was published as a part of the Data Science Blogathon. Introduction Python is a popular and influential programming language used in various applications, from web development to… https://
analyticsvidhya.com/blog/2023/01/5
-upcoming-python-libraries-you-dont-want-to-miss-in-2023/?utm_source=dlvr.it&utm_medium=twitter
… -
Linear and LayerNorm Biases Appear Useless in Experiments
By
–
I'll give it a shot! Btw it is biases in both Linear and LayerNorm that appear to be useless (from my admittedly smaller scale experiments).
-
Filtering and Distillation Techniques for Vision-Language Models
By
–
Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training Radenovic et al.: https://
arxiv.org/abs/2301.02280 #ArtificialIntelligence #DeepLearning #MachineLearning -
LangChain Glossary Documentation Needs Major Update
By
–
we started this a bit here: https://
langchain.readthedocs.io/en/latest/glos
sary.html
… but its massively out of date. if you did want to update this that would be for a lot of folks -
GenBench: Meta AI’s New Generalization Testing Framework for NLP
By
–
GenBench is a new effort led by Meta AI researchers, aims to make state-of-the-art generalization testing the new status quo for NLP work. Learn more about the project and read the paper on the new generalization taxonomy http://
genbench.org -
Vocabulary Size Optimization: 25% Speed Boost Through Kernel Alignment
By
–
The most dramatic optimization to nanoGPT so far (~25% speedup) is to simply increase vocab size from 50257 to 50304 (nearest multiple of 64). This calculates added useless dimensions but goes down a different kernel path with much higher occupancy. Careful with your Powers of 2.
-
ONNX Ecosystem Presentation from Groq Engineer Ramakrishnan
By
–
#FlashbackFriday to Sr. Customer Applications Engineer, Ramakrishnan Sivakumar's November 2021 presentation on the ONNX Ecosystem. This is part of our Lunch & Learn playlist on YouTube featuring @GroqInc employees sharing their wisdom. #ONNX #learning https://
youtu.be/zMgmazDQ8bA -
Deploy HuggingFace LLM Models with DataRobot Custom Models
By
–
See how easy it is to host a large language model from HuggingFace as a DataRobot custom model in only a few minutes. Use the end-to-end notebook in the DataRobot repository, make a copy to edit, and get up to speed with your own model in production. https://
bit.ly/3YhQoST
#LLM