Rodrigo Garcia's starred repositories
LLMs-from-scratch
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
search_with_lepton
Building a quick conversation-based search demo with Lepton AI.
gpt-newspaper
GPT based autonomous agent designed to create personalized newspapers tailored to user preferences.
llama-recipes
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.
Binoculars
Binoculars: Zero-Shot Detection of LLM-Generated Text
Depth-Anything
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
AlphaCodium
Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""
Moore-AnimateAnyone
Character Animation (AnimateAnyone, Face Reenactment)
llm-course
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
scripts-to-rule-them-all
Set of boilerplate scripts describing the normalized script pattern that GitHub uses in its projects.
chess_gpt_eval
A repo to evaluate various LLM's chess playing abilities.
chess_llm_interpretability
Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and representation of player Elo.
open-interpreter
A natural language interface for computers