– Orchestration and ML pipelines This includes converting ML code in modular components to create a connected pipeline for smother deployment and maintenance Pipelines also enable automated training and deployment for the MLOps lifecycle
CODE
-
ML Model Lifecycle: Experiment Tracking and Deployment
By
–
1/ Course overview (Life cycle of ML models) – ML modeling and Experiment tracking:
This includes ML model training and trekking each and every experiment to compare different models & deploy best model
tracking includes model parameters, accuracy measures, & model versioning -
MLOps Zoomcamp Week 1: Introduction and Maturity Model
By
–
Here's an update from week 1 of MLOps Zoomcamp by @DataTalksClub This week was about introduction to MLOps, setting up an environment, and the MLOps maturity model. A thread
-
HuggingChat Adds Model Reply Labeling Feature Training
By
–
New on HuggingChat: you can now label the model's replies with / This provides signal for further model training Try it out and let us know what you think! @huggingface
-
Open-source specifications need significant clarification before release
By
–
12a 12b and 12c cover open-source more clearly. Honestly, they need to clean this up a lot before it goes live. Even the 5d you mention should be 5e.
-
Tree of Thoughts: Advanced Problem Solving Technique for LLMs
By
–
Tree of Thoughts: Deliberate Problem Solving with Large Language Models Yao et al.: https://
arxiv.org/abs/2305.10601 #ArtificialIntelligence #ChatGPT #LargeLanguageModels -
Google Bard analyzes code projects in seconds with AI suggestions
By
–
Nice! #GoogleBard can read your @Replit or @Github projects in less than a second and make suggestions! Prompt by @amasad
-
Developer workflow shift: reliance on ChatGPT for coding
By
–
Ok. Je peux plus coder sans ChatGPT. C'est réelle. (et c'est trop bien. ) Ca doit faire des semaines j'ai pas ouvert StackOverflow…
-
AutoGPT: GPT-4 Open-Source Platform for Complex Task Automation
By
–
Heard of AutoGPT? It is a GPT-4 driven experimental open-source platform that can carry out more complex tasks and multi-step procedures by creating its own prompts and feeding them back to it.@OpenAI @_DigitalIndia @nasscom @GoI_MeitY @NeGD_GoI pic.twitter.com/ENBUJzrXGX
— IndiaAI (@OfficialINDIAai) 20 mai 2023Heard of AutoGPT? It is a GPT-4 driven experimental open-source platform that can carry out more complex tasks and multi-step procedures by creating its own prompts and feeding them back to it. @OpenAI @_DigitalIndia @nasscom @GoI_MeitY @NeGD_GoI
-
Philippe Tillet continues Triton development at OpenAI
By
–
yep though the real story is more that everyone was scared when Philippe (the creator of Triton) got hired at OpenAI that he would stop contributing/pushing Triton (that he created and open-sourced during his PhD) but thankfully he was allowed to continue working on it…