Update model card

README.md

@@ -1,55 +1,89 @@
 ---
 base_model: Qwen/Qwen3-Reranker-4B
+base_model_relation: finetune
 library_name: transformers
 pipeline_tag: text-classification
 tags:
   - text-to-sql
+  - text2sql
+  - nl2sql
   - sql
+  - sql-generation
   - template-matching
+  - template-selection
+  - constrained-decoding
+  - database
   - nli
   - paraphrase
   - reranker
+  - cross-encoder
   - qwen3
 language:
   - en
 license: apache-2.0
 ---
 
-# Qwen3-Reranker-4B — SQL Template Matcher
+# TeCoD SQL Template Matcher
 
-Fine-tune of [`Qwen/Qwen3-Reranker-4B`](https://huggingface.co/Qwen/Qwen3-Reranker-4B) as a cross-encoder NLI classifier over pairs of natural-language questions. Given a user's question and a candidate question (with entity values masked), it predicts whether the user question is paraphrase of candidate question.
+Fine-tune of [`Qwen/Qwen3-Reranker-4B`](https://huggingface.co/Qwen/Qwen3-Reranker-4B) used by [TeCoD](https://github.com/SSLab-CSE-IITB/tecod), a template-guided constrained decoding system for text-to-SQL.
 
-### Inputs
+This model is the TeCoD template-matching reranker. It scores whether a user question matches a retrieved masked question/template, helping TeCoD select recurring SQL templates before generation.
 
-A pair of natural-language questions fed through the tokenizer as a standard cross-encoder input. Order matters — premise must be the masked candidate, hypothesis the raw user question:
-
-```
-Premise:    "Show movies released in _ sorted by popularity desc"
-Hypothesis: "What are the top films from 2010 by viewer count?"
-```
+- Project page: <https://sslab-cse-iitb.github.io/tecod/>
+- Source repository: <https://github.com/SSLab-CSE-IITB/tecod>
+- Base model: <https://huggingface.co/Qwen/Qwen3-Reranker-4B>
+- Training data source: [BIRD](https://bird-bench.github.io/) train split.
 
-Entity values in the premise are masked with a space-padded underscore `_`. All literal types (numbers, strings, dates) use the same token. Swapping the order or using a different masking convention will degrade performance.
+## Intended Use
 
-Training used the tokenizer's default max length with `truncation=True`; BIRD question pairs are typically short (~20–40 tokens each). Very long inputs are untested.
+This model is intended as an internal component of TeCoD and related template-based text-to-SQL systems. It is not a standalone SQL generator. In TeCoD, it is used after vector retrieval and before SQL generation to rerank candidate SQL templates.
 
-### Outputs
+## Training Summary
 
-Three-class logits with this mapping:
+- Base model: `Qwen/Qwen3-Reranker-4B`
+- Architecture: `Qwen3ForSequenceClassification`
+- Data: approximately 1.48M NLI pairs derived from BIRD questions.
+- Positive pairs: template-paired questions, self paraphrases, and partner paraphrases that preserve the SQL template.
+- Negative pairs: hard negatives mined using nearest-neighbor retrieval over masked questions, with both masked and unmasked query variants used during pair construction.
+- Labels: `entailment`, `neutral`, `contradiction`.
+- The `neutral` label is retained for compatibility with a 3-class NLI head but was not used as a training target.
 
-| id | label | Meaning in this task |
-|---:|---|---|
-| 0 | `entailment` | the two questions are similar (correspond to the same SQL template) |
-| 1 | `neutral` | unused at training time; logit is untrained |
-| 2 | `contradiction` | the two questions are not similar |
+## Limitations
 
-Use `softmax(logits)[0]` as the match score (`p(entailment)`).
+- Specialized for masked text-to-SQL question/template matching.
+- Not intended for general NLI, semantic similarity, or SQL generation.
+- Assumes the same masking convention and candidate-template construction used by TeCoD.
+- The `neutral` label is untrained; inference should use entailment vs. contradiction or renormalize over labels `{0, 2}`.
+- Very long question pairs and non-English inputs are not validated.
+- The reranking score is one signal in a larger text-to-SQL pipeline; it does not guarantee final SQL correctness.
 
 ## References
 
+- TeCoD project page: <https://sslab-cse-iitb.github.io/tecod/>
+- TeCoD source repo: <https://github.com/SSLab-CSE-IITB/tecod>
 - Base model: <https://huggingface.co/Qwen/Qwen3-Reranker-4B>
 - Training Data - BIRD Train Set: <https://bird-bench.github.io/>
-- Source repo: <https://github.com/SSLab-CSE-IITB/tecod>
+
+If you use this model as part of TeCoD, please cite:
+
+```bibtex
+@article{10.1145/3769822,
+  author = {Jivani, Smit and Maheshwari, Saravam and Sarawagi, Sunita},
+  title = {Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding},
+  journal = {Proceedings of the ACM on Management of Data},
+  volume = {3},
+  number = {6},
+  pages = {1--26},
+  year = {2025},
+  month = dec,
+  publisher = {Association for Computing Machinery},
+  address = {New York, NY, USA},
+  doi = {10.1145/3769822},
+  url = {https://doi.org/10.1145/3769822}
+}
+```
+
 
 ## License
 
-Apache 2.0
+Apache 2.0