Publish AAP-SQL R1 schema reranker

README.md

@@ -0,0 +1,50 @@
+---
+language:
+- en
+library_name: sentence-transformers
+pipeline_tag: text-ranking
+base_model: cross-encoder/ms-marco-MiniLM-L6-v2
+tags:
+- sentence-transformers
+- text-ranking
+- text2sql
+- schema-linking
+- aap-sql
+---
+
+# AAP-SQL R1 schema reranker
+
+AAP-SQL R1 是完整 AAP-SQL 設定中的 cross-encoder schema 重排器。它對 E2 取回的候選欄位評分，保留前 10 個欄位供後續提示增強使用。
+
+AAP-SQL R1 is the cross-encoder schema reranker used by the full AAP-SQL configuration. It scores the candidates returned by E2 and retains the top 10 columns for prompt augmentation.
+
+## Model details
+
+- Base model: `cross-encoder/ms-marco-MiniLM-L6-v2`
+- Training objective: `BinaryCrossEntropyLoss`
+- Training seed: `42`
+- Training data: schema-ranking examples derived from the BIRD training split and schema descriptions
+- Expected library: `sentence-transformers>=5.1.2`
+
+## Use with AAP-SQL
+
+Download this repository into the path expected by the final runner:
+
+```powershell
+hf download TommyPanLab/AAP-SQL-R1 --local-dir models/cross_encoder_schema_paper_repro
+```
+
+Direct loading:
+
+```python
+from sentence_transformers import CrossEncoder
+
+model = CrossEncoder("TommyPanLab/AAP-SQL-R1")
+scores = model.predict([("user question", "table.column: column description")])
+```
+
+The complete pipeline, required BIRD directory layout, and Gemini 3.1 result are documented in the [AAP-SQL publication branch](https://github.com/Tommyweige/AAP-SQL/tree/codex/final-aap-sql-experiment/AAP-SQL-Original).
+
+## Data and license notice
+
+The training examples were derived from the BIRD benchmark. Review the [BIRD project terms](https://bird-bench.github.io/) before using the model. No additional license has been declared for these fine-tuned weights; the upstream model and dataset terms still apply.

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "sentence_transformers": {
+    "activation_fn": "torch.nn.modules.linear.Identity",
+    "version": "5.1.2"
+  },
+  "transformers_version": "4.57.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9daf42b3042d1fa7e03e7710d1ce26bf40b40d498ff558b126029a47cecda00c
+size 90866412

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}