transformers

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

🧠 A production-grade, agentic RAG platform for portfolio intelligence, combining LangChain, Chroma/FAISS, Hugging Face embeddings, and Ollama with dynamic entity extraction, backend API tool-chaining, and a real-time interactive assistant across deploy-ready frontend, backend, and infrastructure stacks.

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.

Transformer 实时手语识别转语音无障碍系统。Real-time Transformer sign language to speech system.

A Flexible Toolkit for Dense Retrieval

KcBERT/KcELECTRA Fine Tune Benchmarks code (forked from https://github.com/monologg/KoELECTRA/tree/master/finetune)

The next evolution of Agents

Automated question generation and question answering from Turkish texts using text-to-text transformers

Pull high-quality, efficient embeddings for PubMed, arXiv and Wikipedia from Huggingface and use for local LLM inference/Retrieval Augmented Generation (RAG)

Quantum Transformers for High Energy Physics Analysis at the Large Hadron Collider

OpenAI-compatible server with a live view into any HF model's residual stream. pip install brainscope

Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!

GLiNER model in a FastAPI microservice.

A collection of Models, Datasets, DataModules, Callbacks, Metrics, Losses and Loggers to better integrate pytorch-lightning with transformers.

LLMs4OM: Matching Ontologies with Large Language Models

This repository showcases my learning journey through various machine learning algorithms, deep learning concepts, and complete end-to-end data science projects.

A radically simple, reliable, and high performance template to enable you to quickly get set up building multi-agent applications

This repository contains a web application designed to execute relatively compact, locally-operated Large Language Models (LLMs).

A zero-dependency Python module for inspecting and converting coding-agent session files (.jsonl) — Claude Code, Codex, and Pi — into the messages format expected by Hugging Face Transformers.