「ReLLM: Exact Structure for Large Language Model Completions」

What if you could ensure that an LLM only returned specific syntactic structure (e.g. JSON or XML), specific semantic structure (e.g. a date or a number), or even complete templates (e.g. a sentence with a blank to fill in)? What if the model never deviated from that structure? ReLLM is a small Python library I open-sourced (MIT) to get deterministic structure out of any large language model completion. This makes improves the quality (and parsability) of even the smallest models. How does it w

What if you could ensure that an LLM only returned specific syntactic structure (e.g. JSON or XML), specific semantic structure (e.g. a date or a number), or even complete templates (e.g. a sentence with a blank to fill in)? What if the model never deviated from that structure? ReLLM is a small Python library I open-sourced (MIT) to get deterministic structure out of any large language model completion. This makes improves the quality (and parsability) of even the smallest models. How does it w

Webページ

コンテンツ文字数：0 文字

見出し数（H2/H3タグ）：0 個

閲覧数：61 件

2023-05-16 11:10:03

オリジナルページを開く