Instructions to use griffith-bigdata/GRAST-SQL-4B-BIRD-Reranker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use griffith-bigdata/GRAST-SQL-4B-BIRD-Reranker with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("griffith-bigdata/GRAST-SQL-4B-BIRD-Reranker") model = AutoModelForCausalLM.from_pretrained("griffith-bigdata/GRAST-SQL-4B-BIRD-Reranker", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Improve model card with metadata, paper link, and usage example
Verified signatureThis PR improves the model card by: - Adding `pipeline_tag: text-ranking` and `library_name: transformers` metadata. This will enable the "how to use" widget and ensure the model appears in the correct filter on the Hub. - Linking the model to its paper: [Scaling Text2SQL via LLM-efficient Schema Filtering with Functional Dependency Graph Rerankers](https://huggingface.co/papers/2512.16083). - Including the system flow diagram, links to related datasets and other models. - Providing sample usage snippets from the GitHub README for applying GRAST-SQL on custom databases. - Adding the academic citation. Please review and merge this PR if everything looks good.90d89c6
-
Create README.md
Verified signaturef402c01
-
Upload folder using huggingface_hub
Verified signaturef73f19a -
initial commit
Verified signature3f086b1