Upload folder using huggingface_hub

README.md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+base_model: distilbert-base-uncased
+pipeline_tag: text-ranking
+library_name: sentence-transformers
+tags: [cross-encoder, reranker, msmarco]
+language: [en]
+---
+
+# ce-cat-distilbert
+
+MiniLM-L12 cross-encoder reranker trained under the configuration stated in §4 of
+[Askari et al., *"Injecting the BM25 Score as Text Improves BERT-Based Re-rankers"*, ECIR 2023](https://arxiv.org/abs/2301.09728):
+**cross-entropy loss** with **early stopping on validation nDCG@10**.
+
+Paired with [`Amdestya/ce-bm25cat-distilbert`](https://huggingface.co/Amdestya/ce-bm25cat-distilbert) — identical data,
+schedule and seed; the arms differ only in the input construction.
+
+## Input format
+
+```python
+text_a = f"{query}"
+text_b = passage
+# tokenises to: [CLS] query [SEP] passage [SEP]
+```
+
+Matched no-injection baseline. Do NOT inject anything into text_a -- this model has never seen a numeric token there.
+
+
+## Usage
+
+```python
+from sentence_transformers import CrossEncoder
+model = CrossEncoder("Amdestya/ce-cat-distilbert", max_length=256)
+```
+
+Outputs are raw logits (identity activation), unbounded, higher = more relevant.
+
+## Training
+
+| | |
+|---|---|
+| objective | cross-entropy on binary relevance |
+| optimizer | Adam, lr 7e-06 |
+| batch size | 32 |
+| length caps | query 30, passage 200 tokens |
+| stopping | early stopping on msmarco-passage/trec-dl-2020/judged nDCG@10, patience 3 |
+| steps | 20000 |
+| best validation nDCG@10 | 0.6872 |
+| seed | 42 |
+
+Built as a reference artifact for a dissertation study on reproducing IR papers with LLMs.

USAGE.json

@@ -0,0 +1,21 @@
+{
+  "base_model": "distilbert-base-uncased",
+  "trained_as": "cross-encoder CAT (cross-entropy, paper section 4)",
+  "input_format": {
+    "text_a": "{query}",
+    "text_b": "{passage}",
+    "tokenises_to": "[CLS] query [SEP] passage [SEP]",
+    "note": "Matched no-injection baseline. Do NOT inject anything into text_a -- this model has never seen a numeric token there."
+  },
+  "bm25_normalisation": null,
+  "loss": "cross-entropy on binary relevance (BCEWithLogits, num_labels=1)",
+  "stopping": "early stopping on msmarco-passage/trec-dl-2020/judged nDCG@10, patience 3",
+  "max_length": 256,
+  "train_batch_size": 32,
+  "lr": 7e-06,
+  "query_max_tokens": 30,
+  "passage_max_tokens": 200,
+  "steps": 20000,
+  "best_val_ndcg@10": 0.6872370440113406,
+  "paired_with": "Amdestya/ce-bm25cat-distilbert"
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.57.0",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebb7ddba3560fe28b5f58208aa5da7329613b2926f9580284b677ef6f8548dd4
+size 267829484

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}