Upload folder using huggingface_hub

README.md

@@ -0,0 +1,65 @@
+---
+language:
+- en
+- multilingual
+license: apache-2.0
+tags:
+- cross-encoder
+- reranker
+- sentence-transformers
+- ror
+- affiliation-matching
+base_model: cross-encoder/ms-marco-MiniLM-L-12-v2
+datasets:
+- cometadata/ror-pipeline-traces
+pipeline_tag: text-classification
+---
+
+# MS-MARCO MiniLM Reranker for ROR Affiliation Matching
+
+A cross-encoder reranker fine-tuned for Research Organization Registry (ROR) affiliation matching.
+
+## Model Description
+
+This model is fine-tuned from `cross-encoder/ms-marco-MiniLM-L-12-v2` on ROR affiliation matching data.
+It reranks candidate ROR organizations given an affiliation string query.
+
+## Training
+
+- **Base model**: cross-encoder/ms-marco-MiniLM-L-12-v2
+- **Training examples**: 127,011
+- **Training traces**: 2,004
+- **Negative sampling**: Hard negatives from retrieval candidates
+- **Epochs**: 5
+- **Batch size**: 16
+- **Learning rate**: 2e-05
+- **Max sequence length**: 256
+
+## Usage
+
+```python
+from sentence_transformers import CrossEncoder
+
+model = CrossEncoder("cometadata/ms-marco-ror-reranker")
+
+# Score affiliation-candidate pairs
+pairs = [
+    ["University of California, Berkeley", "University of California, Berkeley"],
+    ["University of California, Berkeley", "University of California, Los Angeles"],
+]
+scores = model.predict(pairs)
+print(scores)  # Higher score = better match
+```
+
+## Intended Use
+
+This model is designed for reranking ROR organization candidates in affiliation matching pipelines.
+It should be used after an initial retrieval step (e.g., dense retrieval with Snowflake Arctic).
+
+## Training Data
+
+Trained on traces from `cometadata/ror-pipeline-traces` (affrodb_s2aff_traces config).
+
+## Timestamp
+
+2026-01-07T02:10:33.651817+00:00

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": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "sentence_transformers": {
+    "activation_fn": "torch.nn.modules.linear.Identity",
+    "version": "5.2.0"
+  },
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval/CrossEncoderClassificationEvaluator_val_results.csv

@@ -0,0 +1,6 @@
+epoch,steps,Accuracy,Accuracy_Threshold,F1,F1_Threshold,Precision,Recall,Average_Precision
+1.0,7145,0.9849618140303913,3.103402,0.8828939301042306,1.4461942,0.9314359637774903,0.8391608391608392,0.9246121033789791
+2.0,14290,0.9900795212975356,1.1970022,0.9252669039145908,1.1970022,0.9420289855072463,0.9090909090909091,0.968790857063443
+3.0,21435,0.9933076135737343,0.2688725,0.9496743635287153,0.2688725,0.9651022864019254,0.9347319347319347,0.981994141242729
+4.0,28580,0.9943311550271632,0.829528,0.9576968272620446,-1.8397098,0.9656398104265402,0.9498834498834499,0.9849315596449888
+5.0,35725,0.9947248248169436,3.630054,0.9598562013181545,3.630054,0.9876695437731196,0.9335664335664335,0.9873970721484285

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11073e87658df34d5ec27729a30ff9ed62e88154bd43285c34486344f0b185fb
+size 133464836

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": 256,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}