pytorch

Text to emoji translation via DeepDreaming

Dockerized FastAPI wrapper for OmniVoice — zero-shot TTS for 600+ languages with voice cloning, voice design, and OpenAI-compatible API. GPU & CPU support.

Code Repository for the IndicXNLI paper.

This is a multi-modal fusion method based on VGG16 and FastText for identifying useful information collected from social media platforms.

Fine-tuning BERT and Transformer models for NLP tasks, hands-on notebooks · HuggingFace · PyTorch

Create informative READMEs effortlessly using AI-driven templates with the README Creator powered by Language Model (LLM). Simplify documentation and enhance project communication.

All my experiments with the various transformers and various transformer frameworks available

SAM + CLIP + DIFFUSION for image to edit objects in images using plain text

It is the implementation of paper "Multi-Modal Sarcasm Detection in Twitter with Hierarchical Fusion Model"

Python script to fine tune Open source Video Vision Transformer (ViVit) using HuggingFace Trainer Library

Madlab is an advanced AI development studio designed to streamline the process of dataset management, model training, and evaluation. It combines a robust Node.js/Express backend with a powerful Python-based training engine and a modern React frontend.

Serving large language model with transformers

Engage in a semantic segmentation challenge for land cover description using multimodal remote sensing earth observation data, delving into real-world scenarios with a dataset comprising 70,000+ aerial imagery patches and 50,000 Sentinel-2 satellite acquisitions.

building various transformer model architectures and its modules from scratch.

Code release for "GAN-Tree: An Incrementally Learned Hierarchical Generative Framework for Multi-Modal Data Distributions", ICCV 2019

让 MinerU 在 AMD 显卡上以 vLLM + hybrid-auto-engine 满血运行！ 本项目是对官方文档中 AMD/ROCm 生态支持的有效补充。针对 MinerU 3.x 提供了一套完整的 ROCm 7.x + PyTorch 2.11.0 + vLLM 源码编译与部署方案，解析质量与速度对标 NVIDIA 旗舰显卡。

预训练模型知识量度量竞赛 Baseline F1 0.35 BERTForMaskedLM

🧠 Multimodal Retrieval-Augmented Generation that "weaves" together text and images seamlessly. 🪡

Unsupervised specificity-guided optimization of Image Captioning models to encourage meaningful diversity in the generated captions. Code for the paper Generating Diverse and Meaningful Captions: Unsupervised Specificity Optimization for Image Captioning (Lindh et al., 2018).

Code for paper "Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation" (ICLR'24)