Apple released MLX: A deeplearning framework for machine learning on macOS! You can efficiently train and deploy ML models. The repo also includes examples to run open-source models using MLX, like: – LLaMA 2
– Mixtral 8x7B
– LoRA
– CLIP
– Whisper
– Stable Diffusion
LLMS
-

Apple Releases MLX Deep Learning Framework for macOS Machines
By
–
-
Google DeepMind Announces Gemma Language Model with API Access
By
–
Gemma is a new language model just announced by @GoogleDeepMind
. Run it with an API: -
Fine-tune Google’s Gemma7B efficiently with Ludwig AI
By
–
Off the shelf is good, fine-tuned is better. Here's everything you need to #efficiently fine-tune @Google
's #Gemma7B for your task. Best of all, you can do it with @ludwig_ai
, the open-source declarative framework for building custom #LLMs. -
Managing context and API usage with AI assistants
By
–
I am mainly relying on Assistants instead which I use via an API. With plugins and GPTs – It still boils down to passing context between them and depends on how much of this context you need
-

Mastering NLP: From Foundations to Large Language Models
By
–
Mastering #NLProc from Foundations to #LLMs — Applying Advanced Techniques from Rule-Based to LLMs for Solving Real World Business Problems: https://
amzn.to/3TawZDK (Order now. @PacktPublishing release on May 9)
————
#DataScience #GenerativeAI #AI #MachineLearning #DeepLearning -

Unique search functionality for querying ChatGPT feature leaks
By
–
This niche part is very unique! Proven b/c it even can query from smaller websites like TestingCatalog on topics like "ChatGPT leaked features"
-

Positive feedback on AI search capabilities
By
–
Niiice! I like its search capabilities. It can even build on top of niche topics
-
Discussing the impact of Sora on performance metrics
By
–
Nice numbers! Is this all a Sora effect or smth extra on top?
-
Using OpenAI Assistants API for Custom GPT Functionality
By
–
Custom GPTs are not but OpenAI assistants can. You can create an assistant with the same prompt to make it work via an API.