pytorch

Human parsing model for fashion and virtual try-on applications

This repository contains the code to train flan t5 with alpaca instructions and low rank adaptation.

A PyTorch implementation of DeepSpeech and DeepSpeech2.

NLP model zoo for Russian

Implementation of Multi-Game Decision Transformers in PyTorch

State-of-the-art NLP through transformer models in a modular design and consistent APIs.

Google's BigBird (Jax/Flax & PyTorch) @ 🤗Transformers

Combining ViT and GPT-2 for image captioning. Trained on MS-COCO. The model was implemented mostly from scratch.

A python library for highly configurable transformers - easing model architecture search and experimentation.

Script Buddy v2 is a film script text generation tool built using film scripts from the world's most popular film scripts and GPT2.

A Flexible Toolkit for Dense Retrieval

Bleeding edge vLLM Docker image for the NVIDIA DGX Spark (GB10 / sm_121a).

Multimodal Hashtag Prediction with instagram data & pytorch (2nd Place on OpenResource Hackathon 2019)

Biologically-grounded adversarial training platform: cyclic Wake/Dream/Nightmare/Compress phases that accumulate model robustness without catastrophic forgetting. Dockerized, EU AI Act compliance reporting.

This includes the codebase for EntroPE (Entropy-Guided Dynamic Patch Encoder for Time Series Forecasting) paper.

The official repository for our paper "Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks". We develop a method for analyzing emerging functional modularity in neural networks based on differentiable weight masks and use it to point out important issues in current-day neural networks.

spaCy-wrap is a wrapper library for spaCy for including fine-tuned transformers from Huggingface in your spaCy pipeline allowing you to include existing fine-tuned models within your SpaCy workflow.

Getting started with Hugging Face

(ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation

[IEEE TMM 2022] Official implementation of YDTR: Infrared and Visible Image Fusion via Y-shape Dynamic Transformer