Not yet officially, there's at least one community instruction fine-tuned model on Hugging Face already
CODE
-
Machine Learning Model Deployment Guide and Best Practices
By
–
#MachineLearning model deployment
by Murk Sindhya Memon @DataScienceDojo Read more: https://
buff.ly/3sm9LQw #DataScience #AI #BigData #ML #MI cc: @terenceleungsf @yvesmulkers @pascal_bornet -
Open-source program-form implementation of ARC 1 training tasks released
By
–
Just open-sourced by Michael Hodel: a program-form implementation of each of the 400 training tasks of ARC 1, capable of generating more task instances. I expect this will be very useful to everyone working on ARC. GitHub: https://
github.com/michaelhodel/r
e-arc
…
ArXiv: https://
arxiv.org/abs/2404.07353 -
Devin Implements Safety Controls for Eldritch Website System
By
–
The fact that Devin has implemented both a "Madness Meter" and "ForbiddenKnowledge.js" for the Eldritch website is promising
-
AI System Self-Debugging and Quality Assurance Capabilities
By
–
Debugging its own software by running what it creates and doing some QA. Nifty.
-
OpenAI Releases GPT-4 Turbo for Paid ChatGPT Users
By
–
Our new GPT-4 Turbo is now available to paid ChatGPT users. We’ve improved capabilities in writing, math, logical reasoning, and coding. Source: https://
github.com/openai/simple-
evals
… -
Canvas AI Documentation Lookup Feature Implemented
By
–
Neat, it is looking up documentation from Canvas!
-
Trainer Framework Complexity: Overriding Methods and Logging Issues
By
–
on the other hand you can be someone like me who chose it for ease of use at the beginning of a project and now has overriden almost every single method of the Trainer and has to go to insane lengths to understand basic functionality like logging
-
Easy-to-use platform with hosted datasets and pretrained models
By
–
hey you said it! they make getting started really easy 🙂 and their hosted resources are so nice, like datasets & pretrained models
-
API Cost Tracking and Token Continuation for AI Agents
By
–
There are also a number of additional improvements, such as being able to see the cost per API call. And, if the sub-agent or the orchestrator runs out of tokens in the response, it will continue from where it left off.