PinnedAkshay BallalinGoPenAIBuild ReAct Agents using SLMs from ScratchBuild a function-calling agent using a custom Unsloth model with a LoRA adapter, switching between reasoning and function execution…Sep 29Sep 29
PinnedAkshay BallalinGoPenAIUsing YOLO with CLIP to improve RetrievalIn this article we explore how object detection can be used with embeddings to make retrieval more better.Jul 301Jul 301
PinnedAkshay BallalinGoPenAIBuilding an AI Game Bot Using Imitation Learning and 3D Convolution ResNetUnlocking the Secrets of AI Gaming with Imitation Learning, Motion Analysis, and Google Snake — Learn, Play, and Train Without the Hassle…Jan 42Jan 42
PinnedAkshay BallalinGoPenAIDeep Q Learning with PyTorchSolve the classic CartPole Problem with a mixture of Deep Neural Network and Reinforcement LearningOct 29, 2023Oct 29, 2023
PinnedAkshay BallalinGoPenAIBuilding a Vision Transformer from Scratch in PyTorchBreaking Down the Architecture and Implementation Steps for a State-of-the-Art Image Classification NetworkJun 18, 2023Jun 18, 2023
Akshay BallalinAI AdvancesReinforcement Learning Series — Part 2 — Deep Q LearningDeep Q Learning from scratch with a comparison between FCN and LSTM as the Neural NetworkJul 231Jul 231
Akshay BallalinAI AdvancesReinforcement Learning Series- Part 1: Tabular Q LearningLearn how Reinforcement Learning works with theory and code implementation along with tips and tricks.Jul 16Jul 16
Akshay BallalSupercharge your Tests with CodiumAI Cover-AgentLearn how to use AI to increase your test coverage to make your code robustJun 11Jun 11
Akshay BallalIntroducing EmbedAnythingA Highly Performant lightweight multimodal embedding solutionApr 181Apr 181
Akshay BallalinGoPenAIHow to Train your TransformerIn this article we see some tricks on how to train your transformer. I introduce the concept of warmup, pre-training and fine-tuning.Dec 19, 2023Dec 19, 2023