-
RAG Part 2: Document Chunking
-
RAG Part 1: Hybrid Search
A deep dive into hybrid retrieval - combining BM25 keyword search and semantic vector search using Reciprocal Rank Fusion (RRF).
-
LoRA: Parameter-Efficient Fine-Tuning Explained
A practical guide to fine-tuning pretrained language models, covering dataset preparation, handling class imbalance, custom data collators, and training loops in PyTorch with HuggingFace Transformers. Includes full code and explanations of the mechanics beyond high-level APIs.
-
Fine-Tuning DistilBERT for Text Classification: A Complete Implementation
A practical guide to fine-tuning pretrained language models, covering dataset preparation, handling class imbalance, custom data collators, and training loops in PyTorch with HuggingFace Transformers. Includes full code and explanations of the mechanics beyond high-level APIs.