Stars
Instruction Fine-Tuning of Meta Llama 3.2-3B Instruct on Kannada Conversations. Tailoring the model to follow specific instructions in Kannada, enhancing its ability to generate relevant, context-a…
Draw datasets from within Python notebooks.
Minimalistic 4D-parallelism distributed training framework for education purpose
A quick GUI transcription annotator tool with categories and subcategories.
Open sourced research notebooks by the QuantConnect team.
Convert Obsidian vaults to collection of notes readable by Cosma and Zettlr
Naively combining transformers and Kolmogorov-Arnold Networks to learn and experiment
This repository introduces PIXIU, an open-source resource featuring the first financial large language models (LLMs), instruction tuning data, and evaluation benchmarks to holistically assess finan…
An interactive TypeScript tutorial for beginners
AgentSims is an easy-to-use infrastructure for researchers from all disciplines to test the specific capacities they are interested in.
A set of LangChain Tutorials from my youtube channel
LAVIS - A One-stop Library for Language-Vision Intelligence
This project presents a method based on the Mask R-CNN for solving geometric construction problems of Euclidea, which is an online construction game.
Python version of the Euclidea game for possible reinforcement learning agents
fast-stable-diffusion + DreamBooth
PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"
Fast and memory-efficient exact attention
BabyAI platform. A testbed for training agents to understand and execute language commands.
Suite of human-collected datasets and a multi-task continuous control benchmark for open vocabulary visuolinguomotor learning.
The Arcade Learning Environment (ALE) -- a platform for AI research.
Code for "Unsupervised State Representation Learning in Atari"
A collection of pre-trained RL agents using Stable Baselines3
[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
Official Pytorch Implementation of: "Asymmetric Loss For Multi-Label Classification"(ICCV, 2021) paper
Tools for understanding how transformer predictions are built layer-by-layer