Oct 14, 2025 · 2 min read · This is just a brain dump of what I know right now about doing inference and fine tuning on Apple Silicon Mac as of mid October, 2025 (lot more to cover, WIP): mlx is Apple's open library optimized for Apple silicon mlx is analogous to pytorch but o...
Join discussionMay 6, 2025 · 3 min read · What is Fine-Tuning? Fine-tuning is the process of taking a pre-trained model (like GPT, BERT, LLaMA, etc.) and continuing its training on a smaller, task-specific dataset. The goal is to adapt the model's general knowledge to perform better on a par...
Join discussion
Dec 31, 2024 · 11 min read · Key Highlights Introduction to Llama3: Llama3 is a state-of-the-art language model developed by Meta, designed for high performance in natural language processing tasks. Fine-tuning this model can significantly enhance its capabilities for specific ...
Join discussionNov 12, 2024 · 5 min read · La generación de avatares y personajes únicos con IA está revolucionando múltiples industrias, desde el entretenimiento hasta el marketing digital. En este artículo, exploramos cómo esta tecnología permite crear personajes altamente personalizables u...
Join discussion
Aug 5, 2024 · 6 min read · Is it only me ?? or Do I find Mark Zuckerberg better than Sam Altman and people all over the internet called mark the Goat of AI community and it seems like he might be after all by releasing his latest frontier AI model Llama 3.1 405B which seems l...
Join discussion
Jul 28, 2024 · 12 min read · 1. Introduction Retrieval-Augmented Generation (RAG) models combine retrieval and generation techniques to improve the accuracy and relevance of generated responses in question-answering contexts. By leveraging both retrieval and generation, RAG mode...
Join discussion
Jun 23, 2024 · 13 min read · I've been trying my hand at Transfer Learning and Fine Tuning for a while now. I decided to utilise it for a fun little project around F1. I fine-tuned the EfficientNetB0 image classification model on a F1 car images dataset, so that, given an image ...
NNatasha commented
May 25, 2024 · 2 min read · In this post, I will outline the steps I followed to fine-tune a model using Axolotl and Jarvislabs.ai. This post is based on https://maven.com/parlance-labs/fine-tuning and https://medium.com/@andresckamilo/finetuning-llms-using-axolotl-and-jarvis-a...
Join discussion
Mar 21, 2024 · 4 min read · If you have ever tried to use the Mistral model from Hugging Face you will be provided with multiple options. Two of the most downloaded options are: Mistral-7B-v0.1 Mistral-7B-Instruct-v0.2 But what is the difference between these 2 models? Mistral-...
Join discussionDec 2, 2023 · 3 min read · Overview The goal of the Create Week0 10 Academy-organized Week 0 project is to teach the foundations of data engineering and machine learning. As they go through the Slack Messages Analysis challenge, participants will tackle a variety of Machine Le...
Join discussion