metadata
license: apache-2.0
language:
- en
base_model:
- LiquidAI/LFM2-700M
pipeline_tag: text-generation
library_name: transformers
tags:
- rag
- lfm2
- chunking
This is a simple, pre-release lightweight model for extracting informational chunks from text.
The system prompt used in development was "You are a helpful assistant trained by Liquid AI. Your task is to break down paragraphs into structured sections. Each section must have a 'title' and 'content' field. The output must be a JSON list of these sections."