Implement RAG technique using Langchain, ChromaDB on GPT 3.5 Turbo t for conversational chatbot on a PDF document. — In this blog, we will understand an advanced prompt engineering technique called retrieval augmented generation technique, with hands-on examples using Langchain, ChromaDB, and GPT 3.5 Motivation The field of Natural Language Processing (NLP) has seen significant breakthroughs with the advent of transformer-based models like GPT-3. These language models have the ability…

Parameter Efficient Fine Tuning — LoRA, QLoRA — Concepts — In this blog, we will understand the idea behind Parameter Efficient Fine Tuning (PEFT), and explore LoRA and QLoRA, Two of the most important PEFT methods. We will understnad how PEFT can be used to fine tune the model for domain specific tasks, at the lowest cost and minimal infrastrcuture. Motivation …

Parameter Efficient Fine Tuning — LoRA, QLoRA — Hands-On — In this blog, we will implement LoRA the idea behind Parameter Efficient Fine Tuning (PEFT), and explore LoRA and QLoRA, Two of the most important PEFT methods. We will also be exploring “Weights and Biases” for capturing the training metrics. We will be fine-tuning a small Salesforce codegen 350m parameter…