GitHub repo: https://
github.com/pydantic/pydan
tic-ai
…
_____
Interested in ML/AI Engineering? Sign up for our newsletter for in-depth lessons and get a FREE eBook with 150+ core DS/ML lessons:
CODE
-
Pydantic AI GitHub Repository and ML Engineering Newsletter
By
–
-
PydanticAI: Production-Grade Agentic AI Apps in Python
By
–
PydanticAI: Build production-grade Agentic AI apps in pure Python! PydanticAI offers the same elegance and ease of use as FastAPI, now extending that experience to building production-grade LLM applications. Why PydanticAI? Model-agnostic Type-safe & production-ready
-
GitHub Launches Chat Interface with GPT-4o, Sonnet, O1 Models
By
–
yo.. when did GitHub ship a fully functional chat interface w/ 4o, Sonnet 3.5, O1-min & O1-preview!?
— Vaibhav (VB) Srivastav (@reach_vb) 6 décembre 2024
works quite seamlessly with the GitHub API too – nice!! pic.twitter.com/N8KMk1ycTDyo.. when did GitHub ship a fully functional chat interface w/ 4o, Sonnet 3.5, O1-min & O1-preview!? works quite seamlessly with the GitHub API too – nice!!
-
O1 Inference Architecture: Code Interpreter and Multi-Tool Integration
By
–
Imagine that at each inference step of O1, a code interpreter, search functionality, knowledge file reference, GPTs calls, and function calls are triggered.
-
Postprocessing Features Coming to tidymodels Package
By
–
Postprocessing is coming to tidymodels https://
bit.ly/3ZmYDiH
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Learning Chatbot Development: A 2017 Journey
By
–
Throwback to when I first tried learning how to build a chatbot back in 2017.
-
ChatGPT o1 Image Input Enables High-Quality Flowchart Code Generation
By
–
ChatGPT o1 now has image input capabilities. Which means you can upload a flowchart and ask for high-quality code to build it. *code isn't perfect but better than 4o
-
PaliGemma 2 Running 100% Local On-Device with MLX
By
–
PaliGemma 2 running 100% local, on-device, powered by MLX 🔥
— Vaibhav (VB) Srivastav (@reach_vb) 5 décembre 2024
pic.twitter.com/pSHyu9cfgs https://t.co/xB17RN3M4yPaliGemma 2 running 100% local, on-device, powered by MLX
-
Parameter Optimization in Large Language Models
By
–
Got it… Still, if the rule is you have to have <=124M parameters active per token, where did you save those 9216?