Skip to content

Latest commit

 

History

History
11 lines (8 loc) · 6.23 KB

File metadata and controls

11 lines (8 loc) · 6.23 KB

CompletionsLogprobs

Fields

Field Type Required Description
text_offset List[int] ✔️ The starting character position of each token in the generated text, useful for mapping tokens back to their exact location for detailed analysis.
token_logprobs List[float] ✔️ The log probabilities of each generated token, indicating the model's confidence in selecting each token.
tokens List[str] ✔️ A list of individual tokens generated in the completion, representing segments of text such as words or pieces of words.
top_logprobs List[Dict[str, Any]] ✔️ A list of dictionaries, where each dictionary represents the top alternative tokens considered by the model at a specific position in the generated text, along with their log probabilities. The number of items in each dictionary matches the value of logprobs.