Upload repository_library model package

README.md

@@ -0,0 +1,84 @@
+---
+base_model: sentence-transformers/all-MiniLM-L6-v2
+library_name: transformers
+pipeline_tag: text-classification
+tags:
+- cross-encoder-reranker
+- l2
+- repository-library
+- repository_library_search_stack
+- research-library
+- retrieval
+---
+
+# Cross Encoder Reranker
+
+Reranks retrieved candidates with a cross-encoder scoring pass.
+
+## Model Details
+
+- Artifact type: full fine-tuned model
+- Base model: `sentence-transformers/all-MiniLM-L6-v2`
+- Model ID: `L2`
+- Tier: `repository_library_search_stack`
+- Local mirror: `/arxiv/models/repository_library/cross-encoder-reranker`
+- Source checkpoint: `models/checkpoints/L2`
+
+This repository is part of the `repository_library` model stack and is mirrored from `/data/repository_library/models/checkpoints` for publication under the `PeytonT` namespace.
+
+## Intended Use
+
+- Primary use: Reranks retrieved candidates with a cross-encoder scoring pass.
+- Secondary use: retrieval, ranking, planning, or scientific paper tooling inside the broader Repository Library system, depending on the model family.
+- Out of scope: production safety claims, benchmark claims beyond the bundled experiment config, or use outside the model's narrow training objective without task-specific validation.
+
+## Training Data
+
+This package was trained from the following declared datasets or corpus sources:
+
+- `source:github_repos`
+
+## Training Procedure
+
+- Sources: `github_repos`
+- Input fields: `query, candidate_row`
+- Target fields: `relevance_label`
+- Max samples: `4000`
+- Precision: `bf16`
+- Objective: `cross_entropy`
+- Batch size: `8`
+- Learning rate: `5e-05`
+- Max source tokens: `256`
+- Max target tokens: `256`
+- Max steps: `1000`
+- Notes: Search-stack role added to match models.md coverage; dataset builder may need role-specific supervised labels before promotion.
+
+## Evaluation
+
+- Declared metrics: `accuracy`
+- Status: local experiment artifact mirrored for release; external benchmark reporting has not been standardized across the full model family yet.
+
+## Usage
+
+```python
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+
+repo_id = "PeytonT/cross-encoder-reranker"
+
+tokenizer = AutoTokenizer.from_pretrained(repo_id)
+model = AutoModelForSequenceClassification.from_pretrained(repo_id)
+```
+
+## Limitations
+
+- These model cards reflect the packaged experiment configs and mirrored checkpoint contents, not an independently audited benchmark sheet.
+- Some training datasets are local corpora or exported shards, so reproducibility may require access to the surrounding Repository Library data pipeline.
+- Models in this stack are narrow components of a larger paper-and-repository system and should be validated on downstream tasks before deployment.
+
+## Project Context
+
+Repository Library is a research system for indexing, retrieving, aligning, and reasoning over scientific papers, structured paper content, repositories, and cross-domain links between them.
+
+## Contact
+
+Published under `PeytonT` from the local `repository_library` build.

config.json

@@ -0,0 +1,34 @@
+{
+  "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": "0",
+    "1": "1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.57.6",
+  "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:a3aebe10e0ac4e8815ecfba79cce9e2d476f1f8beb916fcbb5f1088d6fd42861
+size 90867952

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 +1,65 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,223 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.666666666666667,
+  "eval_steps": 200,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.8791329860687256,
+      "learning_rate": 2.45e-05,
+      "loss": 0.6936,
+      "step": 50
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.2845050096511841,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 0.6932,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.37205860018730164,
+      "learning_rate": 4.727777777777778e-05,
+      "loss": 0.6946,
+      "step": 150
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.12644897401332855,
+      "learning_rate": 4.4500000000000004e-05,
+      "loss": 0.6926,
+      "step": 200
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "eval_loss": 0.6942273378372192,
+      "eval_runtime": 2.8684,
+      "eval_samples_per_second": 89.248,
+      "eval_steps_per_second": 29.982,
+      "step": 200
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.24128998816013336,
+      "learning_rate": 4.172222222222222e-05,
+      "loss": 0.6941,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.2091750204563141,
+      "learning_rate": 3.894444444444444e-05,
+      "loss": 0.6928,
+      "step": 300
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.38734951615333557,
+      "learning_rate": 3.6166666666666674e-05,
+      "loss": 0.6919,
+      "step": 350
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.40688276290893555,
+      "learning_rate": 3.338888888888889e-05,
+      "loss": 0.6902,
+      "step": 400
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "eval_loss": 0.69222491979599,
+      "eval_runtime": 2.9811,
+      "eval_samples_per_second": 85.876,
+      "eval_steps_per_second": 28.849,
+      "step": 400
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5329565405845642,
+      "learning_rate": 3.061111111111111e-05,
+      "loss": 0.6853,
+      "step": 450
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 2.0410470962524414,
+      "learning_rate": 2.7833333333333333e-05,
+      "loss": 0.6692,
+      "step": 500
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 2.144829273223877,
+      "learning_rate": 2.5055555555555555e-05,
+      "loss": 0.6764,
+      "step": 550
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.855889320373535,
+      "learning_rate": 2.2277777777777778e-05,
+      "loss": 0.6649,
+      "step": 600
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6971002817153931,
+      "eval_runtime": 2.8952,
+      "eval_samples_per_second": 88.423,
+      "eval_steps_per_second": 29.704,
+      "step": 600
+    },
+    {
+      "epoch": 4.333333333333333,
+      "grad_norm": 4.7590532302856445,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 0.6083,
+      "step": 650
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 6.917613506317139,
+      "learning_rate": 1.6722222222222222e-05,
+      "loss": 0.5853,
+      "step": 700
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.807262420654297,
+      "learning_rate": 1.3944444444444446e-05,
+      "loss": 0.5841,
+      "step": 750
+    },
+    {
+      "epoch": 5.333333333333333,
+      "grad_norm": 5.123489856719971,
+      "learning_rate": 1.1166666666666668e-05,
+      "loss": 0.5277,
+      "step": 800
+    },
+    {
+      "epoch": 5.333333333333333,
+      "eval_loss": 0.7716808319091797,
+      "eval_runtime": 3.1291,
+      "eval_samples_per_second": 81.813,
+      "eval_steps_per_second": 27.484,
+      "step": 800
+    },
+    {
+      "epoch": 5.666666666666667,
+      "grad_norm": 6.377001762390137,
+      "learning_rate": 8.38888888888889e-06,
+      "loss": 0.4782,
+      "step": 850
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.968349933624268,
+      "learning_rate": 5.611111111111112e-06,
+      "loss": 0.5204,
+      "step": 900
+    },
+    {
+      "epoch": 6.333333333333333,
+      "grad_norm": 10.05020809173584,
+      "learning_rate": 2.8333333333333335e-06,
+      "loss": 0.4445,
+      "step": 950
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 8.618692398071289,
+      "learning_rate": 5.555555555555556e-08,
+      "loss": 0.481,
+      "step": 1000
+    },
+    {
+      "epoch": 6.666666666666667,
+      "eval_loss": 0.818778395652771,
+      "eval_runtime": 2.8011,
+      "eval_samples_per_second": 91.392,
+      "eval_steps_per_second": 30.702,
+      "step": 1000
+    },
+    {
+      "epoch": 6.666666666666667,
+      "step": 1000,
+      "total_flos": 397989715968000.0,
+      "train_loss": 0.6234129600524903,
+      "train_runtime": 85.265,
+      "train_samples_per_second": 281.475,
+      "train_steps_per_second": 11.728
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 397989715968000.0,
+  "train_batch_size": 24,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f38fcbf3ca1d1294efd864ff7fb9a8d947ddb7c48164ae7d78a1494c3b3980e
+size 5777