MPX0222forHF

/

SQL-R1-7B

like 5

This PR significantly enhances the model card for the SQL-R1 model by:

• Adding pipeline_tag: text-generation: This tag accurately reflects the model's functionality (Natural Language to SQL generation) and improves its discoverability on the Hugging Face Hub.
• Adding library_name: transformers: Based on the config.json (Qwen2ForCausalLM) and tokenizer_config.json (Qwen2Tokenizer), the model is compatible with the transformers library, enabling the automated "how to use" widget.
• Replacing content with comprehensive GitHub README: The model card content has been updated to reflect the full, detailed information from the project's official GitHub README. This includes sections on news, model weights, documentation, environment setup, quick start, and applications, providing a much richer overview for users.
• Correcting GitHub repository links: The GitHub badge URL and the git clone command in the "Environment Setup" section have been updated to point to the canonical repository: https://github.com/IDEA-FinAI/SQL-R1. The star history badge link has also been updated accordingly.
• Adding Hugging Face paper link badge: An additional badge has been included to link directly to the paper on Hugging Face Papers: SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning.
• Including sample usage: The "Quick Start" shell commands from the GitHub README are now part of the model card, providing clear steps for users to interact with the model.

These updates aim to provide users with complete, accurate, and easily discoverable information about SQL-R1.