You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
By analyzing the linguistic complexity and repetitiveness of the text, PlagSnipe provides accurate insights into the authenticity and originality of written content, helping users identify potential instances of AI-generated text with precision and confidence.
SynthWomb/Synthia: Python project using Hugging Face Transformers for GPT-2 NLP, TensorFlow for model management, and SDXL-Turbo for image processing. DeepFace predicts gender. Simple CLI offers Text-to-image and Image-to-image operations, with a built-in GAN for AI art.
Developed and pre-trained a 20.39M-parameter Punjabi GPT-style base model from scratch, including corpus preparation, tokenizer training, benchmark evaluation, and text generation, using a cleaned Punjabi corpus and local Apple Silicon GPU acceleration.
This repository contains a reproducible pipeline to fine-tune causal language models (GPT-style) on domain-specific datasets. It includes data formats, preprocessing scripts, example training commands (LoRA/PEFT and full fine-tuning), and safety/privacy guidance for medical data.