community deeplearning
deeplearning ai
In the context of AI, "LLM" likely refers to "Large Language Model." A Large Language Model is a type of artificial intelligence model designed to understand and generate human-like text based on vast amounts of training data. These models are capable of performing tasks such as language translation, text generation, question answering, and more.
In the context of large language models like GPT-3, "prompting" refers to the input or instructions provided to the model in order to elicit a desired output. When you interact with a language model, you provide a prompt that specifies what you want the model to do or generate.
Token is all about 4 char or 3/4 of word.
In chat gpt 3.5 to tal token should be 4000 by adding input(prompt, message) and output
Supervised learning is a category of machine learning where an algorithm learns to map input data to desired output labels based on a training dataset. In supervised learning, the algorithm is "supervised" by providing it with labeled examples to learn from, which means each input data point is associated with a corresponding correct output label. The goal of supervised learning is to learn a mapping function that can accurately predict or classify new, unseen data.
- Reduce number of token used in prompt
- skip some chains of the workflow when not needed for the task
- Easier to test include human in a loop
- for complex task, keep track of state,
external to LLM(in your own code)
- use external tools (web search, database)
- More focus (Break down a complec task)
- content limitations (max token for input prompt and output response)
- Reduce costs (pay per token)