transformers

Incorporate Image, Text and Tabular Data with HuggingFace Transformers

Finetune Web UI is a user-interface for training and deploying pre-trained models.

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

Comprehensive LLMs repo, where I cover both theoretical and practical aspects of LLMs.

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.

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

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

NeuroLens is a premium, state-of-the-art Document Retrieval-Augmented Generation (RAG) system. It combines an immersive, holographic, sci-fi-themed React frontend with a high-performance FastAPI backend.

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.

CatIss is an intelligent tool for automatic categorization of issue reports based on the RoBERTa model.

Having fun with ML

An HF's Smolagent to automate molecular dynamics simulations using GROMACS.

Convert images into captivating audio stories using image-to-text, language models, and text-to-speech technologies. Upload images, generate stories, and listen to the narrated audio clips. A fun project combining AI and creativity.

Use Transformers.js from Blazor WebAssembly to run pretrained models with the ONNX Runtime in the browser.

🧠🃏 Your universal model catalog, everything, everywhere, all at once.

Transformers PHP is a toolkit for PHP developers to add machine learning magic to their projects easily.

Convert pretrained RoBerta models to various long-document transformer models

Experiments with multimodal deep learning models based on transformers

7.67× LoRA / 8.35× Full FT speedup for Qwen3.5 (0.8B–27B) on NVIDIA DGX Spark — wall-clock parity with rented H100. Lossless within BF16. Three-command interactive wizard handles model picker, data validator, training, and merge.