Marco's starred repositories
ThunderKittens
Tile primitives for speedy kernels
Mixture-of-depths
Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"
comfyui-inpaint-nodes
Nodes for better inpainting with ComfyUI: Fooocus inpaint model for SDXL, LaMa, MAT, and various other tools for pre-filling inpaint & outpaint areas.
OpenCodeInterpreter
OpenCodeInterpreter is a suite of open-source code generation systems aimed at bridging the gap between large language models and sophisticated proprietary systems like the GPT-4 Code Interpreter. It significantly enhances code generation capabilities by integrating execution and iterative refinement functionalities.
KwaiAgents
A generalized information-seeking agent system with Large Language Models (LLMs).
InnoDesAIgn
Un sofware che incorpora diversi modelli per ottenre un'efficace ed efficiente incorporazione di oggetti con sfondi
SuperAdapters
Finetune ALL LLMs with ALL Adapeters on ALL Platforms!
llama-telegram-bot
A simple telegram chat bot for LLMs supported by llama.cpp
multi_loras
Load multiple LoRA modules simultaneously and automatically switch the appropriate combination of LoRA modules to generate the best answer based on user queries.
aphrodite-engine
PygmalionAI's large-scale inference engine
DeepImageBlending
This is a Pytorch implementation of deep image blending
nixtla
TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.
Finetune_LLMs
Repo for fine-tuning Casual LLMs
Harmonizer
High-Resolution Image/Video Harmonization [ECCV 2022]