Something I was working on at the @agihouse_org hackathon over the weekend The LLMChain (prompt template + llm + output parser) is a core, modular component and is where most customization happens. Understanding this is crucial for understanding LangChain!
CODE
-
Flash Attention 2 Integration Reduces Lit-GPT Runtime by 11%
By
–
My colleagues already added Flash Attention 2 to our Lit-GPT repo!
So if you are working on the NeurIPS LLM Efficiency Challenge (for which Lit-GPT is the official starter kit, https://
llm-efficiency-challenge.github.io), you can shave ~11% off your total runtime -
Chainlit: Python Framework for Rapid LLM Application Development
By
–
GitHub – Chainlit/chainlit: Build Python LLM apps in minutes
https://bit.ly/42QIzFn #AI #MachineLearning #DeepLearning #LLMs #DataScience -
BenchLLM: Open-source testing library for LLM validation
By
–
BenchLLM by @V7Labs is a Python-based open-source library that streamlines the testing of Large Language Models (LLMs) and AI-powered applications. It measures the accuracy of your model, agents, or chains by validating responses on any number of tests via LLMs.
-
Neural Networks Computer Vision Deep Learning Toolbox Integration
By
–
Explore prediction, visualization, and seamless integration with Computer Vision Toolbox and Deep Learning Toolbox.
— MathWorks (@MathWorks) 24 juillet 2023
Watch now 👉 https://t.co/OvysKOZhNq#NeuralNetworks #ComputerVision #ModelBasedDesign pic.twitter.com/OPClilqLn1Explore prediction, visualization, and seamless integration with Computer Vision Toolbox and Deep Learning Toolbox. Watch now http://
spr.ly/6014PHeHO #NeuralNetworks #ComputerVision #ModelBasedDesign -
Graph Neural Networks Tutorial in TensorFlow at ICML
By
–
Graph neural networks (GNNs) are commonly used to learn from graph data. Today during the #ICML2023 EXPO Day at 3pm, drop by the “Graph Neural Networks in TensorFlow” tutorial to get hands-on experience on how to effectively implement GNNs in #TensorFlow.
-
API Bots Enable Unlimited Control Over Bot Output
By
–
Also remember that in addition to prompt bots (which this change applies to), we also allow anyone to create an API bot, which allows unlimited control over bot output: https://
developer.poe.com/api-bots/quick
-start
… -
Multimodal LLM with Vision-Language Transformer and LangChain
By
–
Using the `Vision-and-Language Transformer` model and @LangChainAI to create a Multimodal LLM in @Streamlit! 🔥
— Charly Wargnier (@DataChaz) 23 juillet 2023
– Demo app: https://t.co/miwwtiUxv0
– ViLT model: https://t.co/nz8npLUs9o
– App creator: @nicolas_tch pic.twitter.com/iTWuMwgc8WUsing the `Vision-and-Language Transformer` model and @langchain to create a Multimodal LLM in @Streamlit
! – Demo app: https://
vilt-gpt-ppn83ly4c9.streamlit.app
– ViLT model: https://
huggingface.co/dandelin/vilt-
b32-finetuned-vqa
…
– App creator: @nicolas_tch -
Building Strong Tech Foundations with Proper Software Design and Architecture
By
–
Building a solid foundation for your tech solutions starts with the right Software Design and architecture stack! Via @ingliguori #TechTips #Coding #BigData #Analytics #DataScience #AI #Python #RStats #TensorFlow #Java #JavaScript #ReactJS #CloudComputing #DEVCommunity #code