Upload folder using huggingface_hub

README.md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+base_model: google/bert_uncased_L-4_H-256_A-4
+library_name: onnx
+pipeline_tag: feature-extraction
+tags:
+- sentence-transformers
+- embeddings
+- scientific-papers
+- distillation
+- onnx
+- int8
+- wasm
+- research-library
+datasets:
+- PeytonT/1m_papers_text
+- PeytonT/paper_universe_interactive
+language:
+- en
+---
+
+# M1-Lite Paper Embedding Model ONNX
+
+This is a compact student encoder distilled from `PeytonT/1m-paper-embedding-model` over the 1M paper corpus.
+It predicts the same 768-dimensional, L2-normalized M1 embedding space used by the Research Library paper universe.
+
+## Files
+
+| Path | Description |
+| --- | --- |
+| `onnx/model.onnx` | Float ONNX student encoder. |
+| `onnx/model.int8.onnx` | Dynamically quantized int8 ONNX model for browser/WASM inference. |
+| `tokenizer/` | Student tokenizer files. |
+| `manifest.json` | Export metadata consumed by the static viewer. |
+
+## Training
+
+- teacher target: `exports/huggingface/paper_universe_interactive_v1/semantic_m1/papers_all.emb.i8`
+- interactive level: `exports/huggingface/paper_universe_interactive_v1/interactive/papers_all.json`
+- rows: `1,000,000`
+- final eval cosine vs M1 targets: `0.7351`
+- final eval MSE vs M1 targets: `0.000690`
+- int8 ONNX size: `33.7 MB`
+
+## Embedding Format
+
+- output name: `embedding`
+- shape: `[batch, 768]`
+- pooling: attention-mask mean pooling, projection to 768 dimensions, L2 normalization
+- intended max sequence length: `128`
+
+The output is compatible with the existing `semantic_m1/*.emb.i8` paper-vector files.

checkpoints/step-1000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b779a15ca9406caf791e1f53754d7339b44eb26f10b49e9818575d9f8eacd497
+size 135980363

checkpoints/step-2000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d925c23dce69396d1a1f8468a9c9f805c9b60fdbe9a0092fb7593b39d07a852f
+size 135980363

checkpoints/step-3000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c0849da8aaa8638cab787c862f2932c84b03ffd4ec9e54ee70c5dac25e192dc
+size 135980363

checkpoints/step-4000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1aa4dc7ec490aad4fe6051b2f8678216085affbb580059345eeab6419f682d0
+size 135980363

checkpoints/step-5000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab9bbdef4b272b5701c413997f58f3ad8211c60ca3a9a3634bbcdddf8f3f1583
+size 135980363

checkpoints/step-6000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9c0392316bd243a8a4a160bd5543904c87fc318b816e6bab101787f478bebd4
+size 135980363

checkpoints/step-7000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f7aa2955d015f191a5a62d7c668c785679dabea2e4f6f710f48238d0f893910
+size 135980363

manifest.json

@@ -0,0 +1,29 @@
+{
+  "browser_note": "Same input and output names as the full M1 SciBERT ONNX export; can query semantic_m1 paper vector files.",
+  "built_at": 1777171028,
+  "dimension": 768,
+  "interactive_level": "exports/huggingface/paper_universe_interactive_v1/interactive/papers_all.json",
+  "model_kind": "m1_lite_distilled_embedding",
+  "normalization": "l2",
+  "onnx": "onnx/model.onnx",
+  "pooling": "mean_pool_attention_mask_project_l2_normalized",
+  "quantized_onnx": "onnx/model.int8.onnx",
+  "scale": 127.0,
+  "sequence_length": 128,
+  "source_dir": "/arxiv/huggingface/paper_text_1m_dedup_v1",
+  "student_id": "google/bert_uncased_L-4_H-256_A-4",
+  "target_embeddings": "exports/huggingface/paper_universe_interactive_v1/semantic_m1/papers_all.emb.i8",
+  "teacher_base_id": "allenai/scibert_scivocab_uncased",
+  "teacher_id": "PeytonT/1m-paper-embedding-model",
+  "tokenizer": "tokenizer",
+  "train_stats": {
+    "eval_cosine": 0.7350965235382318,
+    "eval_mse": 0.0006898527972225565,
+    "final_cosine": 0.739337682723999,
+    "final_loss": 0.2609059512615204,
+    "global_steps": 7813,
+    "missing_texts": 0,
+    "rows": 1000000,
+    "train_seconds": 473.90148282051086
+  }
+}

onnx/model.int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:990eaeb36042b83b014796f2aa4b479fc56f64239cdded8be266375b246829f2
+size 35376665

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df46ca7344ceff011e8198b4d436fcdf0ffbc1ef6cd274a0ae7fd7c6c4ab7ed
+size 45289801

pytorch/config.json

@@ -0,0 +1,18 @@
+{
+  "model_type": "m1_lite_distilled_embedding",
+  "output_dim": 768,
+  "pooling": "mean_pool_attention_mask_project_l2_normalized",
+  "student_id": "google/bert_uncased_L-4_H-256_A-4",
+  "teacher_base_id": "allenai/scibert_scivocab_uncased",
+  "teacher_id": "PeytonT/1m-paper-embedding-model",
+  "train_stats": {
+    "eval_cosine": 0.7350965235382318,
+    "eval_mse": 0.0006898527972225565,
+    "final_cosine": 0.739337682723999,
+    "final_loss": 0.2609059512615204,
+    "global_steps": 7813,
+    "missing_texts": 0,
+    "rows": 1000000,
+    "train_seconds": 473.90148282051086
+  }
+}

pytorch/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29b1bd3f06aba867d8094882d954ba5a0e077af0ae4036976bbe9d61ec6f3f26
+size 45502626

tokenizer/special_tokens_map.json

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

tokenizer/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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": 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]"
+}