DeepSeek-R1 explored
Why DeepSeek-R1 was a significant step for Open Source AI.
LLM
A view on BLT
Byte Latent Transformer (BLT), a tokenizer-free architecture for NLP.
LLM Quantization in a nutshell
An exploration of LLM quantization methods.
What is PEFT?
Fine-tuning of Large Language Models with Parameter Efficient.
Hands on with Retrieval Augmented Generation
Build a Chatbot that uses Retrieval Augmented Generation to retrieve domain specific knowledge.