Tag Archives: llm

Customizing LLMs: Prompt Engineering

Prompt Engineering or Prompting is the fundamental LLM customization technique. It is the process of designing effective prompts to guide an LLM’s response. It is simple, low-cost, and requires no model modifications.

In this post, we will explore some common prompting techniques such as:

  1. Zero-Shot Prompting – Asking the LLM to answer without prior examples.
  2. Few-Shot Prompting – Providing a few examples in the prompt to improve accuracy.
  3. Chain-of-Thought (CoT) Prompting – Encouraging step-by-step reasoning to enhance complex problem-solving.
  4. Meta Prompting – Guide the reasoning process by introducing structure, constraints, or multi-step instructions.
  5. Self-Consistency Prompting – Generate multiple solutions and select the most frequently appearing answer.
  6. Tree of Thought (ToT) Prompting – Exploring multiple reasoning paths before selecting an answer.
  7. Prompt Chaining – Not exactly a prompting technique, it is using the output of the previous prompt as input to the next prompt.
Read More

LLM Customization

A large language model or LLM is a type of machine learning model designed for natural language processing or NLP. These models have an extremely high number of parameters (trillions as of this writing) and are trained on vast amounts of human-generated and human-consumed data. Due to their extensive training on this data, LLMs develop predictive capabilities in syntax, semantics, and knowledge within human language. This enables them to generate coherent and contextually relevant responses, giving the impression of intelligence.

Read More

Transformer²: Self-Adaptive LLMs

LLMs are typically developed through a process of training on vast amounts of data, the corpus. This costs a lot of time and money. ChatGPT-3, for example, cost $10M. This cost going down but it’s remains expensive. You can avoid this cost for specific use cases by “fine-tuning” a model with specific data or you can augment their prompts with reference data as in Retrieval Augmented Generation or RAG. The next stage in LLM development are models that update/evolve through time. This is what’s discussed in Sakana AI’s paper Transformer²: Self-Adaptive LLMs.

Running Your Own LLM With Ollama

Leveraging the capabilities of Large Language Models (LLM) using APIs such as the OpenAI APIs is an easy way to add intelligence and advanced functionality to your applications. However, token costs add up and they can get quite expensive. Then there’s the nagging question of privacy and security. Finally, you’re limited in your ability to experiment and customize. But if you have a powerful machine with a GPU or two sitting around, wouldn’t it be great to utilize it for running one of those open source LLMs? Here’s how you can do it.

Read More

Amazon Gets Into the LLM Game with Nova

Amazon just got into the LLM arena with Amazon Nova. And they announced not one, not two, but SIX models!

  1. Amazon Nova Micro: Text-only model delivering low-latency responses, ideal for language understanding, translation, reasoning, and code completion.
  2. Amazon Nova Lite: Low-cost multimodal model, lightning-fast for processing text, image, and video inputs, suitable for interactive and high-volume applications.
  3. Amazon Nova Pro: High-capability multimodal model with top accuracy, speed, and cost efficiency for diverse tasks, excelling at instruction following and agentic workflows.
  4. Amazon Nova Premier: Coming soon. Likely a premium version of Nova Pro with more features and/or better performance.
  5. Amazon Nova Canvas: Advanced image generation model for creating and editing professional-grade images from text or image prompts.
  6. Amazon Nova Reel: Video generation model enabling high-quality video creation from text and images, with natural language controls for style and pacing.

The LLM landscape just got bigger and better!