Upload ConvMemory v2 evidence reranker checkpoint (v0.5.0)

MANIFEST.json

@@ -0,0 +1,32 @@
+{
+  "candidate_pool": "ConvMemory v1 top10 from dense MPNet top500",
+  "forbidden_inference_inputs": [
+    "gold",
+    "gold_ids",
+    "is_current",
+    "is_latest",
+    "is_stale",
+    "stale",
+    "answer",
+    "answer_text",
+    "ce_score",
+    "mxbai_score",
+    "teacher_score",
+    "gpt_label",
+    "entity_id",
+    "slot_id"
+  ],
+  "format": "convmemory_evidence_reranker",
+  "inference_inputs": [
+    "query text",
+    "candidate memory text",
+    "candidate id",
+    "optional position/time metadata"
+  ],
+  "seed": 7,
+  "source_experiment": "v361_top10_evidence_reranker.py",
+  "teacher_weight": 0.0,
+  "train_split": "LoCoMo dev split via choose_split(dev_ratio=0.5, seed=7)",
+  "training_target": "gold-only listwise retrieval CE",
+  "version": "0.5.0"
+}

README.md

@@ -0,0 +1,86 @@
+---
+library_name: sentence-transformers
+pipeline_tag: text-ranking
+tags:
+- convmemory
+- reranking
+- conversational-memory
+- cross-encoder
+- evidence-reranker
+license: mit
+---
+
+# ConvMemory v2 Evidence Reranker
+
+This is the ConvMemory v0.5.0 protected top-10 token-evidence reranker checkpoint.
+It is intended to be attached to the base ConvMemory LoCoMo/MPNet checkpoint:
+`Purdy0228/ConvMemory-LoCoMo-MPNet`.
+
+## Usage
+
+```python
+from convmemory import ConvMemory
+
+model = ConvMemory.from_pretrained("Purdy0228/ConvMemory-LoCoMo-MPNet")
+model.load_evidence_reranker("Purdy0228/ConvMemory-v2-Evidence-Reranker")
+
+ranked = model.retrieve(
+    query=query,
+    memories=memories,
+    evidence_reranker="v2",
+    top_k=10,
+)
+```
+
+The repository layout is compatible with `convmemory.EvidenceReranker.from_pretrained`:
+
+- `evidence_reranker_config.json`
+- `MANIFEST.json`
+- `cross_encoder/` SentenceTransformers CrossEncoder checkpoint
+
+## What It Does
+
+ConvMemory v2 preserves the exact ConvMemory v1 top-10 candidate set and only
+reorders that protected prefix using token-level query/memory evidence. It cannot
+recover a gold memory that v1 failed to retrieve into top-10.
+
+## Training
+
+- Source experiment: `experiments/v361_top10_evidence_reranker.py`
+- Seed: 7
+- Base model: `cross-encoder/ms-marco-MiniLM-L-6-v2`
+- Training target: gold-only listwise retrieval cross-entropy
+- Teacher weight: 0.0
+- Candidate pool: ConvMemory v1 top-10 from dense MPNet top-500
+
+## Headline Evaluation
+
+Canonical v361 5-seed headline, reported in the ConvMemory repository:
+
+- ConvMemory v1 FULL MRR: 0.5824
+- ConvMemory v2 FULL MRR: 0.6560
+- Delta: +0.0734, paired bootstrap 95% CI [+0.0645, +0.0827]
+
+The v364 load-bearing ablation retrained the same full-text arm in an ablation
+harness and obtained FULL MRR 0.6677. Text perturbations collapsed:
+
+- no memory text: 0.2966
+- random other-query text: 0.2506
+- shuffled memory text: 0.2731
+- scalar only: 0.5792
+
+## Anti-Leak Discipline
+
+The public inference API rejects gold-defining or post-hoc fields such as:
+`gold`, `gold_ids`, `is_current`, `is_latest`, `is_stale`, `stale`, `answer`,
+`answer_text`, `ce_score`, `mxbai_score`, `teacher_score`, `gpt_label`,
+`entity_id`, and `slot_id`.
+
+Inference inputs are query text, candidate id/text, optional candidate position
+or time metadata, and the protected v1 top-10 candidate set.
+
+## Limitations
+
+- LoCoMo-specific fine-tuning; validate or retrain before using cross-domain.
+- Recall-preserving over v1 top-10, not a replacement for candidate generation.
+- Not a full top-500 cross-encoder. It is a bounded precision stage after v1.

cross_encoder/README.md

@@ -0,0 +1,146 @@
+---
+tags:
+- sentence-transformers
+- cross-encoder
+- reranker
+pipeline_tag: text-ranking
+library_name: sentence-transformers
+---
+
+# CrossEncoder
+
+This is a [Cross Encoder](https://www.sbert.net/docs/cross_encoder/usage/usage.html) model trained using the [sentence-transformers](https://www.SBERT.net) library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Cross Encoder
+<!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
+- **Maximum Sequence Length:** 256 tokens
+- **Number of Output Labels:** 1 label
+- **Supported Modality:** Text
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Documentation:** [Cross Encoder Documentation](https://www.sbert.net/docs/cross_encoder/usage/usage.html)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
+- **Hugging Face:** [Cross Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=cross-encoder)
+
+### Full Model Architecture
+
+```
+CrossEncoder(
+  (0): Transformer({'transformer_task': 'sequence-classification', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'logits'}}, 'module_output_name': 'scores', 'architecture': 'BertForSequenceClassification'})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import CrossEncoder
+
+# Download from the 🤗 Hub
+model = CrossEncoder("cross_encoder_model_id")
+# Get scores for pairs of inputs
+pairs = [
+    ['How many calories in an egg', 'There are on average between 55 and 80 calories in an egg depending on its size.'],
+    ['How many calories in an egg', 'Egg whites are very low in calories, have no fat, no cholesterol, and are loaded with protein.'],
+    ['How many calories in an egg', 'Most of the calories in an egg come from the yellow yolk in the center.'],
+]
+scores = model.predict(pairs)
+print(scores)
+# [ 9.8896 -2.073   0.0997]
+
+# Or rank different texts based on similarity to a single text
+ranks = model.rank(
+    'How many calories in an egg',
+    [
+        'There are on average between 55 and 80 calories in an egg depending on its size.',
+        'Egg whites are very low in calories, have no fat, no cholesterol, and are loaded with protein.',
+        'Most of the calories in an egg come from the yellow yolk in the center.',
+    ]
+)
+# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Framework Versions
+- Python: 3.12.3
+- Sentence Transformers: 5.4.1
+- Transformers: 5.8.0
+- PyTorch: 2.8.0+cu128
+- Accelerate: 
+- Datasets: 4.8.5
+- Tokenizers: 0.22.2
+
+## Citation
+
+### BibTeX
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

cross_encoder/config.json

@@ -0,0 +1,36 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "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,
+  "is_decoder": false,
+  "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",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.8.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

cross_encoder/config_sentence_transformers.json

@@ -0,0 +1,11 @@
+{
+  "__version__": {
+    "pytorch": "2.8.0+cu128",
+    "sentence_transformers": "5.4.1",
+    "transformers": "5.8.0"
+  },
+  "activation_fn": "torch.nn.modules.linear.Identity",
+  "default_prompt_name": null,
+  "model_type": "CrossEncoder",
+  "prompts": {}
+}

cross_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1cd3bf011c49efd5681b40dfba4166a39c6be38520200c9f66d77a191e8b264
+size 90866412

cross_encoder/modules.json

@@ -0,0 +1,8 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.base.modules.transformer.Transformer"
+  }
+]

cross_encoder/sentence_bert_config.json

@@ -0,0 +1,10 @@
+{
+    "transformer_task": "sequence-classification",
+    "modality_config": {
+        "text": {
+            "method": "forward",
+            "method_output_name": "logits"
+        }
+    },
+    "module_output_name": "scores"
+}

cross_encoder/tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "is_local": true,
+  "local_files_only": false,
+  "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]"
+}

evidence_reranker_config.json

@@ -0,0 +1,5 @@
+{
+  "cross_encoder_model": "cross-encoder/ms-marco-MiniLM-L-6-v2",
+  "max_length": 256,
+  "top_k": 10
+}