Kye Gomez's Projects
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Tutorial from Pytorch that shows how to train a translation model but made very beautiful using shapeless
Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%
Generate instruction tuning datasets with multiple agents running on trees of thoughts for hyper-efficient extraction of reasoning tokens
Transformer Implementation in Triton
The Cloud of Clouds framework unifying all clouds ☁️ into a radically simple interface.
Implementation of Google's USM speech model in Pytorch
Versatile Diffusion: Text, Images and Variations All in One Diffusion Model, 2022
Open source implementation of a vision transformer that can understand Videos using max vit as a foundation.
My simple implementation of "VIMA: General Robot Manipulation with Multimodal Prompts"
Open source scripts to create large scale datasets with rich detail for multi-modal models
Implementation of Vision Mamba from the paper: "Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model" It's 2.8x faster than DeiT and saves 86.8% GPU memory when performing batch inference to extract features on high-res images
VisualChatGPT
An plug in and play pipeline that utilizes segment anything to segment datasets with rich detail for downstream fine-tuning on vision models like CLIP, ViT, Imagebind, and so on!
[ICLR 2023 Spotlight] Vision Transformer Adapter for Dense Predictions
Open source implementation of "Vision Transformers Need Registers"
WARP: Warp Speed Protocol Commit Message ShortHand Framework
Transform youtube URL into text 100x faster with whisperx
Build high-performance AI models with modular building blocks
A simple No Code and Drag N Drop platform to build SOTA AI models using the Zeta framework!