Alex Punnen – Medium

Alex Punnen

Pinned

Published in
Better ML

Exploring Large Language Models

Language Understanding, Task Generalization, Causal Reasoning, Explainability/Hallucinations, Quantisation, Fine-Tuning via Instruct…

Sep 4, 2023

Exploring Large Language Models

Sep 4, 2023

Pinned

Published in
Better ML

Image pre-processing for TF Serving via OpenCV, Pillow, TensorFlow tf.image.decode*

Example Input Images

Mar 29, 2019

Image pre-processing for TF Serving via OpenCV, Pillow, TensorFlow tf.image.decode*

Mar 29, 2019

Pinned

Published in
Better Software

Optimizing any TensorFlow model using TensorFlow Transform Tools and using TensorRT

Model Optimization and reducing precision from FP32 to FP 16 for speedup and reducing graph size.

Apr 25, 2019

Optimizing any TensorFlow model using TensorFlow Transform Tools and using TensorRT

Apr 25, 2019

Pinned

Backpropagation Deep Dive

Back Propagation with Softmax output and CrossEntropy Loss

Feb 26, 2022

Backpropagation Deep Dive

Feb 26, 2022

Pinned

Published in
Better Software

From Data Warehouse to Data Lake to Data Lakehouse

What’s for what, what you need, and what are the advantages and limitations

Jul 4, 2022

From Data Warehouse to Data Lake to Data Lakehouse

Jul 4, 2022

Jan 21 2025 Is a very bad day

I am not political and not on any one side or another. Every country and leader can do what they want to improve their country and…

Jan 21

Jan 21 2025 Is a very bad day

Jan 21

Published in
Towards AI

Compression is Generalisation, Generalisation is Intelligence - Unsupervised Learning in Large…

The predictive power of compression in large language models

Nov 22, 2024

Compression is Generalisation, Generalisation is Intelligence - Unsupervised Learning in Large…

Nov 22, 2024

US Elections 2024- A thought

The future is unpredictable. The question on everyone's mind is the US Presidential election

Nov 3, 2024

Nov 3, 2024

Published in
Towards Data Science

Leveraging Smaller LLMs for Enhanced Retrieval-Augmented Generation (RAG)

Llama-3.2–1 B-Instruct and LanceDB

Oct 18, 2024

Leveraging Smaller LLMs for Enhanced Retrieval-Augmented Generation (RAG)

Oct 18, 2024

Published in
Techlogs

GPU Compute vs GPU memory load time

GPUs 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 6, 2024

GPU Compute vs GPU memory load time

Oct 6, 2024

Alex Punnen

Alex Punnen

SW Architect/programmer- in various languages and technologies from 2001 to now. https://www.linkedin.com/in/alexpunnen/

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams