the PyTorch codebase is 27 million tokens.
OPEN SOURCE
-
MLX Framework Generates Excitement Similar to Jupyter Discovery
By
–
I feel like the last time I’ve had as much fun as I have had messing around with mlx was like when I discovered Jupyter for the first time?
-
Moondream Streamlit App Updated to Version 2 Model
By
–
My Moondream Streamlit app has been updated to v2 of the model. Incredible work! @vikhyatk
-
LangChain Deepens Google Cloud Database Integration for Developers
By
–
We're thrilled to announce LangChain now has deeper integration with Google Cloud databases. Developers now have access to a suite of open source LangChain packages that are more flexible and customizable when working with Google Cloud's database portfolio. Read more below!
-
Fine-tuning and Structured Generation for Reliable JSON Output with LLMs
By
–
Fine-tuning + structured generation = improved #JSON generation with #LLMs! Check out our blog and benchmarks to learn how you can reliably output JSON with open-source frameworks #LoRAX and #Outlines, and Predibase.
-
Open Source Libraries Documentation Feedback Initiative
By
–
Don't like our docs? Let us know! We've recently added / buttons to each documentation page for our open source libraries Help us improve our docs by quickly leaving us invaluable feedback!
-
Deploy Mistral Large to Azure with LangChain Python
By
–
Deploy Mistral Large to Azure and create a conversation with Python and LangChain Great blogs from our friends at @neondatabase on how to deploy Mistral Large in an enterprise-friendly Azure container and then use with LangChain Blog: https://
neon.tech/blog/deploy-mi
stral-large-to-azure-and-chat-with-langchain
… -
PyTorch Labs GPT-Fast Repository Link Shared
By
–
Repo: https://
github.com/pytorch-labs/g
pt-fast
… -
PyTorch Releases GPT-Fast for Efficient Text Generation
By
–
Pytorch released GPT-fast!⚡️
— Sumanth (@Sumanth_077) 5 mars 2024
This is a simple and efficient implementation of pytorch-native transformer text generation:
Here are some key features:
– Very low latency
– <1000 lines of python
– No dependencies other than PyTorch and sentencepiece
– int8/int4 quantization
-… pic.twitter.com/chk4ms5nf6Pytorch released GPT-fast! This is a simple and efficient implementation of pytorch-native transformer text generation: Here are some key features: – Very low latency
– <1000 lines of python
– No dependencies other than PyTorch and sentencepiece
– int8/int4 quantization
– -
Exploring Ultralytics Explorer API for Computer Vision Applications
By
–
🚀 Blog-tastic Tuesdays 🚀https://t.co/Fw7qlUCixR
— Satya Mallick (@LearnOpenCV) 5 mars 2024
🔍 Excited to delve into the world of computer vision with the Ultralytics Explorer API! Join us as we explore its functionalities and real-world applications on a custom wildlife dataset. #ComputerVision #Ultralytics… pic.twitter.com/3BEgtNkHaIBlog-tastic Tuesdays https://
learnopencv.com/ultralytics-ex
plorer-api/
… Excited to delve into the world of computer vision with the Ultralytics Explorer API! Join us as we explore its functionalities and real-world applications on a custom wildlife dataset. #ComputerVision #Ultralytics