README.md

metadata

license: llama2

TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios

We introduce TableLLM-7b, a robust large language model (LLM) with 7 billion parameters, purpose-built for proficiently handling tabular data manipulation tasks, whether they are embedded within documents or spreadsheets, catering to real-world office scenarios.

TLLM-7b is fine-tuned based on CodeLlama-Instruct-7b and generates either a code solution or a direct text answer to handle tabular data manipulation tasks based on different scenarios. Code generation is used for the insert, delete, update, query, and plot operations of tables. Text generation is used for the query operation of short tables.