Vikas Kumar OjhainGeek CultureHow I Built My Own ChatLLM to Explain Me Python in ChatGPT ToneThis blog describes how to finetune an LLM model to explain the Python code in chatGPT tone i.e. in the same way chatGPT does.·7 min read·Dec 11, 2023--2--2
Vikas Kumar OjhainGeek CultureOptimizing Parseq OCR: Adding Quantization Support for Enhanced EfficiencyI recently added the quantization support for OCR Parseq. This blog explains how you can use the same to optimize your own model.·6 min read·Sep 3, 2023----
Vikas Kumar OjhainGeek CultureGiving Language Models the Ability to See Without Retraining or Fine-TuningThis blog explains how we can give language models ability to see without retraining or fine-tuning them with a modularized approach.·6 min read·Jul 14, 2023----
Vikas Kumar OjhaDetecting Objects With Precision: Polygonal Bounding Box-Based Object DetectionThis blog explains how we can detecting slanted objects accurately using Polygonal bounding boxes instead of rectangular ones.·11 min read·Jun 8, 2023----
Vikas Kumar OjhainGeek CultureSay Goodbye to Tedious Annotation: Annotate Object for Segmentation By WordsThis blog explains how we can annotate images by just passing the object names to the pipeline proposed in this blog.·8 min read·Apr 25, 2023----
Vikas Kumar OjhainGeek CultureExploring Open Source Alternatives to Chat GPTThis blog explores different open source alternatives of ChatGPT.·8 min read·Apr 17, 2023----
Vikas Kumar OjhainGeek CultureUsing Python Code in Android Studio With ChaquopyThis blog demonstrates how we can use python code in android studio with the help of Chaquopy.·7 min read·Mar 19, 2023--1--1
Vikas Kumar OjhainGeek CultureBinary Neural Networks: A Game Changer in Machine LearningThis blog explains about binary neural networks which have potential of revolutionizing deep learning if proper efforts are made.·9 min read·Feb 19, 2023--2--2
Vikas Kumar OjhainGeek CultureTraining Larger Models Over Your Average GPU With Gradient Checkpointing in PyTorchMost of us have faced situations where our model is too big to train on our GPU. This blog explains how we can solve it through a example.·8 min read·Jan 30, 2023----
Vikas Kumar OjhainGeek CulturePruning and Quantizing YOLO V7 With ModoptimaThis blog explains how you can use my library modoptima to optimize YOLO V7 with few lines and code and boost your inference by 3–10 times.·7 min read·Jan 15, 2023--4--4