machinelearning icon indicating copy to clipboard operation
machinelearning copied to clipboard

Ensure tiktoken implementation up-to-date with OpenAI reference implementation

Open stephentoub opened this issue 1 year ago • 1 comments

The implementation at https://github.com/openai/tiktoken/commits/main/src/lib.rs has seen several improvements in the last year (eg https://github.com/openai/tiktoken/pull/255), including a couple that claim perf wins around algorithmic complexity for long inputs. The comments in the source also cite ways of avoiding needing an LRU cache. We should ensure the C# implementation has all the corresponding goodness.

stephentoub avatar Feb 20 '24 16:02 stephentoub

cc: @tarekgh

stephentoub avatar Feb 20 '24 16:02 stephentoub