PinnedAlex PunneninBetter MLExploring Large Language ModelsLanguage Understanding, Task Generalization, Causal Reasoning, Explainability/Hallucinations, Quantisation, Fine-Tuning via Instruct…Sep 4, 2023Sep 4, 2023
PinnedAlex PunneninBetter MLImage pre-processing for TF Serving via OpenCV, Pillow, TensorFlow tf.image.decode*Example Input ImagesMar 29, 20191Mar 29, 20191
PinnedAlex PunneninBetter SoftwareOptimizing any TensorFlow model using TensorFlow Transform Tools and using TensorRTModel Optimization and reducing precision from FP32 to FP 16 for speedup and reducing graph size.Apr 25, 20193Apr 25, 20193
PinnedAlex PunnenBackpropagation Deep DiveBack Propagation with Softmax output and CrossEntropy LossFeb 26, 2022Feb 26, 2022
PinnedAlex PunneninBetter SoftwareFrom Data Warehouse to Data Lake to Data LakehouseWhat’s for what, what you need, and what are the advantages and limitationsJul 4, 20224Jul 4, 20224
Alex PunnenUS Elections 2024- A thoughtThe future is unpredictable. The question on everyone's mind is the US Presidential election4d ago4d ago
Alex PunneninTowards Data ScienceLeveraging Smaller LLMs for Enhanced Retrieval-Augmented Generation (RAG)Llama-3.2–1 B-Instruct and LanceDBOct 185Oct 185
Alex PunneninTechlogsGPU Compute vs GPU memory load timeGPUs are great in parallel tasks because, unlike 10 or 20 threads of a CPU, the number of threads in a GPU is in the thousands to say at a…Oct 6Oct 6
Alex PunneninalexpunnenLove will find a wayWhat thats precious but cannot hold As like water it slips through Cannot contain as it has to be free like air But like air to breath or…Jul 3Jul 3