Upload repository_library model package

README.md

@@ -0,0 +1,89 @@
+---
+base_model: allenai/scibert_scivocab_uncased
+library_name: peft
+pipeline_tag: feature-extraction
+tags:
+- embeddings
+- m6
+- paper-fulltext-embedding
+- papers
+- repository-library
+- research-library
+- scientific-papers
+- t3_paper_text
+---
+
+# Paper Fulltext Embedding
+
+Produces embeddings over full paper text for retrieval and clustering tasks.
+
+## Model Details
+
+- Artifact type: LoRA adapter
+- Base model: `allenai/scibert_scivocab_uncased`
+- Model ID: `M6`
+- Tier: `T3_paper_text`
+- Local mirror: `/arxiv/models/repository_library/paper-fulltext-embedding`
+- Source checkpoint: `models/checkpoints/m6`
+
+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 embeddings over full paper text for retrieval and clustering tasks.
+- 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:
+
+- `local/paper_text_2m_dedup_v1`
+- `source:paper_text_parquet`
+
+## Training Procedure
+
+- Sources: `paper_text_parquet`
+- Input fields: `title, abstract, text`
+- Target fields: `fulltext_embedding`
+- Max samples: `0`
+- Precision: `bf16`
+- Objective: `contrastive`
+- Batch size: `4`
+- Learning rate: `0.0001`
+- Max source tokens: `512`
+- Max target tokens: `128`
+- 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
+from peft import PeftModel
+
+repo_id = "PeytonT/paper-fulltext-embedding"
+base_id = "allenai/scibert_scivocab_uncased"
+
+tokenizer = AutoTokenizer.from_pretrained(repo_id)
+base = AutoModel.from_pretrained(base_id)
+model = PeftModel.from_pretrained(base, 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.

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "allenai/scibert_scivocab_uncased",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query",
+    "value"
+  ],
+  "target_parameters": null,
+  "task_type": "FEATURE_EXTRACTION",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29e8bb9630f550fe53f5762eda60b0d440aa8c768bf2ee28f9828482bf19e1d2
+size 1186088

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 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "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": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,223 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.046296296296296294,
+  "eval_steps": 200,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0023148148148148147,
+      "grad_norm": 0.3478386700153351,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.5384,
+      "step": 50
+    },
+    {
+      "epoch": 0.004629629629629629,
+      "grad_norm": 0.42086708545684814,
+      "learning_rate": 9.900000000000002e-06,
+      "loss": 0.5451,
+      "step": 100
+    },
+    {
+      "epoch": 0.006944444444444444,
+      "grad_norm": 0.4326656460762024,
+      "learning_rate": 1.49e-05,
+      "loss": 0.4839,
+      "step": 150
+    },
+    {
+      "epoch": 0.009259259259259259,
+      "grad_norm": 0.4516472816467285,
+      "learning_rate": 1.9900000000000003e-05,
+      "loss": 0.4111,
+      "step": 200
+    },
+    {
+      "epoch": 0.009259259259259259,
+      "eval_loss": 0.349865585565567,
+      "eval_runtime": 19.7692,
+      "eval_samples_per_second": 12.949,
+      "eval_steps_per_second": 12.949,
+      "step": 200
+    },
+    {
+      "epoch": 0.011574074074074073,
+      "grad_norm": 0.5795977711677551,
+      "learning_rate": 2.4900000000000002e-05,
+      "loss": 0.2866,
+      "step": 250
+    },
+    {
+      "epoch": 0.013888888888888888,
+      "grad_norm": 0.35750141739845276,
+      "learning_rate": 2.9900000000000002e-05,
+      "loss": 0.199,
+      "step": 300
+    },
+    {
+      "epoch": 0.016203703703703703,
+      "grad_norm": 0.6528739333152771,
+      "learning_rate": 3.49e-05,
+      "loss": 0.1817,
+      "step": 350
+    },
+    {
+      "epoch": 0.018518518518518517,
+      "grad_norm": 0.33804208040237427,
+      "learning_rate": 3.99e-05,
+      "loss": 0.1493,
+      "step": 400
+    },
+    {
+      "epoch": 0.018518518518518517,
+      "eval_loss": 0.1466292142868042,
+      "eval_runtime": 19.6974,
+      "eval_samples_per_second": 12.997,
+      "eval_steps_per_second": 12.997,
+      "step": 400
+    },
+    {
+      "epoch": 0.020833333333333332,
+      "grad_norm": 0.5409814119338989,
+      "learning_rate": 4.49e-05,
+      "loss": 0.1559,
+      "step": 450
+    },
+    {
+      "epoch": 0.023148148148148147,
+      "grad_norm": 0.7483624219894409,
+      "learning_rate": 4.99e-05,
+      "loss": 0.1437,
+      "step": 500
+    },
+    {
+      "epoch": 0.02546296296296296,
+      "grad_norm": 1.4873676300048828,
+      "learning_rate": 5.4900000000000006e-05,
+      "loss": 0.1234,
+      "step": 550
+    },
+    {
+      "epoch": 0.027777777777777776,
+      "grad_norm": 0.17527984082698822,
+      "learning_rate": 5.99e-05,
+      "loss": 0.1333,
+      "step": 600
+    },
+    {
+      "epoch": 0.027777777777777776,
+      "eval_loss": 0.11654040217399597,
+      "eval_runtime": 19.671,
+      "eval_samples_per_second": 13.014,
+      "eval_steps_per_second": 13.014,
+      "step": 600
+    },
+    {
+      "epoch": 0.03009259259259259,
+      "grad_norm": 0.6555693745613098,
+      "learning_rate": 6.49e-05,
+      "loss": 0.1308,
+      "step": 650
+    },
+    {
+      "epoch": 0.032407407407407406,
+      "grad_norm": 1.7553420066833496,
+      "learning_rate": 6.99e-05,
+      "loss": 0.1187,
+      "step": 700
+    },
+    {
+      "epoch": 0.034722222222222224,
+      "grad_norm": 0.5994613170623779,
+      "learning_rate": 7.49e-05,
+      "loss": 0.1056,
+      "step": 750
+    },
+    {
+      "epoch": 0.037037037037037035,
+      "grad_norm": 0.1644933968782425,
+      "learning_rate": 7.99e-05,
+      "loss": 0.1135,
+      "step": 800
+    },
+    {
+      "epoch": 0.037037037037037035,
+      "eval_loss": 0.10061360150575638,
+      "eval_runtime": 19.6346,
+      "eval_samples_per_second": 13.038,
+      "eval_steps_per_second": 13.038,
+      "step": 800
+    },
+    {
+      "epoch": 0.03935185185185185,
+      "grad_norm": 0.9034128189086914,
+      "learning_rate": 8.49e-05,
+      "loss": 0.1126,
+      "step": 850
+    },
+    {
+      "epoch": 0.041666666666666664,
+      "grad_norm": 0.14649496972560883,
+      "learning_rate": 8.99e-05,
+      "loss": 0.1173,
+      "step": 900
+    },
+    {
+      "epoch": 0.04398148148148148,
+      "grad_norm": 0.24131137132644653,
+      "learning_rate": 9.49e-05,
+      "loss": 0.1048,
+      "step": 950
+    },
+    {
+      "epoch": 0.046296296296296294,
+      "grad_norm": 0.7404407858848572,
+      "learning_rate": 9.99e-05,
+      "loss": 0.1042,
+      "step": 1000
+    },
+    {
+      "epoch": 0.046296296296296294,
+      "eval_loss": 0.09243285655975342,
+      "eval_runtime": 19.9298,
+      "eval_samples_per_second": 12.845,
+      "eval_steps_per_second": 12.845,
+      "step": 1000
+    },
+    {
+      "epoch": 0.046296296296296294,
+      "step": 1000,
+      "total_flos": 0.0,
+      "train_loss": 0.2129466395378113,
+      "train_runtime": 353.5445,
+      "train_samples_per_second": 11.314,
+      "train_steps_per_second": 2.828
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cbd2e6b7d9591fec0d3363e606d73506aeb64c89d55474a8df841375236f9da
+size 5841