Upload repository_library model package

README.md

@@ -0,0 +1,85 @@
+---
+base_model: sentence-transformers/all-MiniLM-L6-v2
+library_name: transformers
+pipeline_tag: feature-extraction
+tags:
+- code
+- embeddings
+- file-embedding
+- r2
+- repositories
+- repository-library
+- research-library
+- t4_repo
+---
+
+# File Embedding
+
+Produces file-level dense representations for retrieval and matching.
+
+## Model Details
+
+- Artifact type: full fine-tuned model
+- Base model: `sentence-transformers/all-MiniLM-L6-v2`
+- Model ID: `R2`
+- Tier: `T4_repo`
+- Local mirror: `/arxiv/models/repository_library/file-embedding`
+- Source checkpoint: `models/checkpoints/R2`
+
+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: Produces file-level dense representations for retrieval and matching.
+- 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: `file_query`
+- Target fields: `source_chunk`
+- Max samples: `4000`
+- Precision: `bf16`
+- Objective: `contrastive`
+- Batch size: `8`
+- Learning rate: `5e-05`
+- Max source tokens: `256`
+- Max target tokens: `256`
+- Max steps: `1000`
+
+## Evaluation
+
+- Declared metrics: `recall_at_10, ndcg_at_10`
+- 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 AutoModel, AutoTokenizer
+
+repo_id = "PeytonT/file-embedding"
+
+tokenizer = AutoTokenizer.from_pretrained(repo_id)
+model = AutoModel.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 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "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",
+  "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 sha256:7174b34a56c70ebe77869d1d1e6ac0d423b81fa9f3dcfa6dd664ae50cd4d8c04
+size 90864192

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": 0.1161554679274559,
+      "learning_rate": 2.45e-05,
+      "loss": 0.2385,
+      "step": 50
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.02218211442232132,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 0.1177,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.00968642346560955,
+      "learning_rate": 4.727777777777778e-05,
+      "loss": 0.116,
+      "step": 150
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.007011748850345612,
+      "learning_rate": 4.4500000000000004e-05,
+      "loss": 0.1083,
+      "step": 200
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "eval_loss": 0.06607545167207718,
+      "eval_runtime": 5.6176,
+      "eval_samples_per_second": 45.571,
+      "eval_steps_per_second": 15.309,
+      "step": 200
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.006341904401779175,
+      "learning_rate": 4.172222222222222e-05,
+      "loss": 0.1148,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.003990900237113237,
+      "learning_rate": 3.894444444444444e-05,
+      "loss": 0.1187,
+      "step": 300
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.002797077177092433,
+      "learning_rate": 3.6166666666666674e-05,
+      "loss": 0.1147,
+      "step": 350
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.004016134887933731,
+      "learning_rate": 3.338888888888889e-05,
+      "loss": 0.1186,
+      "step": 400
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "eval_loss": 0.0658242404460907,
+      "eval_runtime": 5.4416,
+      "eval_samples_per_second": 47.045,
+      "eval_steps_per_second": 15.804,
+      "step": 400
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.007220633793622255,
+      "learning_rate": 3.061111111111111e-05,
+      "loss": 0.1079,
+      "step": 450
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.01633382774889469,
+      "learning_rate": 2.7833333333333333e-05,
+      "loss": 0.1124,
+      "step": 500
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.42010870575904846,
+      "learning_rate": 2.5055555555555555e-05,
+      "loss": 0.113,
+      "step": 550
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.009207644499838352,
+      "learning_rate": 2.2277777777777778e-05,
+      "loss": 0.1064,
+      "step": 600
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.0652749314904213,
+      "eval_runtime": 5.5368,
+      "eval_samples_per_second": 46.236,
+      "eval_steps_per_second": 15.532,
+      "step": 600
+    },
+    {
+      "epoch": 4.333333333333333,
+      "grad_norm": 0.2730109393596649,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 0.0993,
+      "step": 650
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 0.005696973763406277,
+      "learning_rate": 1.6722222222222222e-05,
+      "loss": 0.0892,
+      "step": 700
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.9231644868850708,
+      "learning_rate": 1.3944444444444446e-05,
+      "loss": 0.0979,
+      "step": 750
+    },
+    {
+      "epoch": 5.333333333333333,
+      "grad_norm": 0.151046484708786,
+      "learning_rate": 1.1166666666666668e-05,
+      "loss": 0.0911,
+      "step": 800
+    },
+    {
+      "epoch": 5.333333333333333,
+      "eval_loss": 0.06247705966234207,
+      "eval_runtime": 5.4795,
+      "eval_samples_per_second": 46.719,
+      "eval_steps_per_second": 15.695,
+      "step": 800
+    },
+    {
+      "epoch": 5.666666666666667,
+      "grad_norm": 0.051675036549568176,
+      "learning_rate": 8.38888888888889e-06,
+      "loss": 0.0851,
+      "step": 850
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.010107653215527534,
+      "learning_rate": 5.611111111111112e-06,
+      "loss": 0.0998,
+      "step": 900
+    },
+    {
+      "epoch": 6.333333333333333,
+      "grad_norm": 0.14959843456745148,
+      "learning_rate": 2.8333333333333335e-06,
+      "loss": 0.0862,
+      "step": 950
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 0.1443173885345459,
+      "learning_rate": 5.555555555555556e-08,
+      "loss": 0.0863,
+      "step": 1000
+    },
+    {
+      "epoch": 6.666666666666667,
+      "eval_loss": 0.06236131116747856,
+      "eval_runtime": 5.5424,
+      "eval_samples_per_second": 46.19,
+      "eval_steps_per_second": 15.517,
+      "step": 1000
+    },
+    {
+      "epoch": 6.666666666666667,
+      "step": 1000,
+      "total_flos": 0.0,
+      "train_loss": 0.11109923124313355,
+      "train_runtime": 166.7816,
+      "train_samples_per_second": 143.901,
+      "train_steps_per_second": 5.996
+    }
+  ],
+  "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": 0.0,
+  "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 sha256:0486e2ced4478591587cd4f8eeb7b64fad1a0079b70a0b04b78fffefb5775e0b
+size 5841