Python 排行榜

Low-Resource LLM Fine-Tuning using Unsloth and LoRA/QLoRA (WSL2/Linux) 🧠

AI/ML research project on AMD ROCm

A Bert2Bert model which able to generate headlines!

This application utilizes the powerful Florence-2 vision-language model from Microsoft to generate comprehensive captions for images. The model is capable of understanding visual content and expressing it in natural language.

In this end to end project I have built a RAG app using ObjectBox Vector Databse and LangChain. With Objectbox you can do OnDevice AI, without the data ever needing to leave the device.

Runtime detector for reward hacking and misalignment in LLM agents (89.7% F1 on 5,391 trajectories).

1st Prize for Creativity at Agents & MCP Hackathon 2025. Transform raw footage into viral-ready content in seconds. No skills required. No expensive gear needed. Just your vision and our AI.

Final training script from HuggingFace Whisper Fine tuning event - to get best results on finetuned model.

HFDownloader - Hugging Face Model Downloader

Fast and practical image deraining with PyTorch.

Build LLM-enabled FastAPI applications without build configuration.

Welcome to the Document QA system! This repository contains the code for a system that allows you to ask questions about your documents and get answers based on their contents. It supports a wide range of document formats, including PDF, Word, Excel, PowerPoint, text files, and even images!

FastText Pytorch version

Realism Adapter for Flux.1 Dev

Comparing Selective Masking Methods for Depression Detection in Social Media

[ACL 2026 Oral] Official code, UIQ benchmark, and pretrained checkpoints for "Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval" (Yoo et al., Sogang University)

A repository that implements multiple Rectified Flow (RF)-based image editing approaches built upon the 🤗 Diffusers library.

A zero-shot relation extractor, easily downloadable from the HuggingFace repo.

Indonesian news summarization with IndoBART / mT5 (headline + paragraph summary).

An automated solution for fact-checking using available claims and fake-news datasets to fine-tune state-of-the-art language models published recently for NLP tasks (BERT, RoBERTa, XLNet, ConvBERT...) in order to classify unseen claims.