Decode with Greedy Sampling
Easy · Solved in PyTorch · Machine learning coding practice
Problem
In Large Language Model (LLM) inference, Greedy Sampling (or Greedy Search) is the most straightforward decoding strategy. It is a deterministic algorithm that selects the most likely next token at each step of the generation process.
Topics: transformer, inference, llm, pytorch
The full statement, worked examples, hints and the test suite are available once you sign in. You can then solve Decode with Greedy Sampling in the browser and run it against the tests.