+/-12 lines of code in gpt-fast integrated Gemma from @GoogleDeepMind ; and shows:
* 234 tokens / sec on V100 in int8
* 144 tokens / sec on V100 in float precision https://
github.com/pytorch-labs/g
pt-fast/commit/ef055fc12188eaf80d8ba948ad743ee5583d0f3c
…
MACHINE LEARNING
-
GPT-Fast Integrates Gemma with Optimized Token Performance
By
–
-
Semantic Chunking: Three Methods for Document Splitting
By
–
Semantic Chunking Semantic chunking using embedding distances between sentences to figure out how to split a document. A key decision is what threshold to split at. We now support three methods: Percentile
Interquartile Range
Standard Deviation Big shout out to -
GTR Model Embeddings Bug Fix and Post-Processing Correction
By
–
unfortunately that's due to a bug I made when training the model; the gtr embeddings i use are missing a last post-processing step. someone trained a fixed model, more info here https://
github.com/jxmorris12/vec
2text/issues/28
… -
50% Discount on ODSC East AI Mini-Bootcamp February 29 March 1
By
–
On Feb. 29 and March 1, you can save 50% on #ODSCEast’s AI Mini-Bootcamp. Become an #AI Expert in 2024. Register now: https://
bit.ly/3RJDP2e by @_odsc ————
#DataScience #MachineLearning #DeepLearning #DataScientists #GenerativeAI #Coding #BigData #ComputerVision #NLProc #ODSC -
Human Preference Predictor Architecture and Results
By
–
This is the architecture of my preference predictor. You can read more about how it works and the results here. https://
huyenchip.com/2024/02/28/pre
dictive-human-preference.html
… As always, feedback is much appreciated! -
Weak Models Match Strong Models on Simple Prompts
By
–
In my experiment, a preference predictor was able to pick up the performance patterns of different models. One pattern is that for simple prompts, weak models can do (nearly) as well as strong models. For more challenging prompts, however, users are much more likely to prefer
-
YOLOv9: Advanced Object Detection with PGI and GELAN
By
–
🚀 New Blog Alert 🚀https://t.co/hrquazDYeg
— Satya Mallick (@LearnOpenCV) 29 février 2024
Excited to explore #YOLOv9, the latest breakthrough in object detection technology? Pioneered by Chien-Yao Wang and his team, YOLOv9 introduces groundbreaking techniques like PGI and GELAN, setting new standards in efficiency and… pic.twitter.com/ifiOYfMYj8New Blog Alert https://
learnopencv.com/yolov9-advanci
ng-the-yolo-legacy/
… Excited to explore #YOLOv9, the latest breakthrough in object detection technology? Pioneered by Chien-Yao Wang and his team, YOLOv9 introduces groundbreaking techniques like PGI and GELAN, setting new standards in efficiency and -
Are Video Generation Models World Simulators?
By
–
Are Generation Models World Simulators? https://
artificialcognition.net/posts/video-ge
neration-world-simulators/
… -
Scikit-LLM: Integrating Large Language Models with Scikit-Learn
By
–
Introducing Scikit-LLM: Scikit-Learn Meets Large Language Models! You can seamlessly integrate powerful language models like ChatGPT into scikit-learn for enhanced text analysis tasks. Here's what you can do with Scikit-LLM: 1. Zero-Shot Text Classification
2. Few-Shot Text -
Abacus AI Enterprise MLOps and LLMOps Platform Solutions
By
–
#Statistics & #MachineLearning #infographics from @AbacusAI Learn about their incredibly COMPLETE Enterprise #MLOps & #LLMOps Platforms and Solutions at http://
abacus.ai
——
#BigData #DataScience #AI #DeepLearning #DataScientists #LLMs #NeuralNetworks #NLProc #AIStrategy