cycloneboy

/

CscSQL-Merge-Qwen2.5-Coder-3B-Instruct

like 0

This PR adds a comprehensive model card for the CscSQL-Grpo-Qwen2.5-Coder-7B-Instruct model, based on the paper CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement Learning.

The model card includes:

• Essential metadata such as pipeline_tag: text-generation and library_name: transformers to ensure the model is easily discoverable and correctly categorized on the Hugging Face Hub.
• Relevant tags like text-to-sql, sql, and qwen2, along with datasets and base_model for better context.
• A link to the official paper and its abstract.
• A link to the GitHub repository for access to the code and more project details.
• An overview of the model's approach, main results, and a table of related models and datasets.
• A clear "How to Use" section with a Python code snippet demonstrating inference with the transformers library, tailored for Text-to-SQL generation using the model's specific chat template.
• The BibTeX citation for proper academic attribution.

This update significantly improves the model's documentation, making it more accessible and user-friendly on the Hugging Face Hub.