Upload folder using huggingface_hub

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 128,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,148 @@
+---
+language:
+- en
+license: apache-2.0
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+- modernbert
+- embeddings
+pipeline_tag: sentence-similarity
+datasets:
+- mjbommar/ogbert-v1-mlm
+model-index:
+- name: ogbert-2m-sentence
+  results:
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STSBenchmark
+      type: mteb/stsbenchmark-sts
+    metrics:
+    - type: spearman_cosine
+      value: 0.453
+  - task:
+      type: STS
+    dataset:
+      name: MTEB STS12
+      type: mteb/sts12-sts
+    metrics:
+    - type: spearman_cosine
+      value: 0.396
+---
+
+# OGBert-2M-Sentence
+
+A tiny (2.1M parameter) ModernBERT-based sentence embedding model for glossary and domain-specific text.
+
+**Related models:**
+- [mjbommar/ogbert-2m-base](https://huggingface.co/mjbommar/ogbert-2m-base) - Base MLM model for fill-mask tasks
+
+## Model Details
+
+| Property | Value |
+|----------|-------|
+| Architecture | ModernBERT + Mean Pooling + L2 Normalize |
+| Parameters | 2.1M |
+| Hidden size | 128 |
+| Layers | 4 |
+| Attention heads | 4 |
+| Vocab size | 8,192 |
+| Max sequence | 1,024 tokens |
+| Embedding dim | 128 (L2 normalized) |
+
+## Training
+
+- **Pretraining**: Masked Language Modeling on domain-specific glossary corpus
+- **Dataset**: [mjbommar/ogbert-v1-mlm](https://huggingface.co/datasets/mjbommar/ogbert-v1-mlm)
+- **Key finding**: L2 normalization of embeddings is critical for clustering/retrieval performance
+
+## Performance
+
+### Semantic Textual Similarity (MTEB STS)
+
+Spearman correlation between model similarity scores and human judgments on sentence pairs.
+
+| Task | OGBert-2M | BERT-base | RoBERTa-base |
+|------|----------:|----------:|-------------:|
+| STSBenchmark | 0.453 | 0.473 | 0.545 |
+| BIOSSES | 0.489 | 0.547 | 0.582 |
+| STS12 | **0.396** | 0.309 | 0.321 |
+| STS13 | 0.460 | 0.599 | 0.563 |
+| STS14 | 0.388 | 0.477 | 0.452 |
+| STS15 | 0.500 | 0.603 | 0.613 |
+| STS16 | 0.474 | 0.637 | 0.620 |
+| **Average** | **0.451** | 0.521 | 0.528 |
+
+OGBert-2M achieves **87% of BERT-base** STS performance with **52x fewer parameters**. Outperforms both baselines on STS12.
+
+### Document Clustering (ARI)
+
+Evaluated on 80 domain-specific documents across 10 categories using Spherical KMeans.
+
+| Model | Params | ARI |
+|-------|--------|-----|
+| **OGBert-2M-Sentence** | **2.1M** | **0.797** |
+| BERT-base | 110M | 0.896 |
+| RoBERTa-base | 125M | 0.941 |
+
+### Document Retrieval (MRR)
+
+Mean Reciprocal Rank for same-category document retrieval.
+
+| Model | Params | MRR | P@1 |
+|-------|--------|-----|-----|
+| **OGBert-2M-Sentence** | **2.1M** | **0.973** | **0.963** |
+| BERT-base | 110M | 0.994 | - |
+| RoBERTa-base | 125M | 0.989 | - |
+
+### Summary vs Baselines
+
+At 1/50th the size, OGBert-2M-Sentence achieves:
+- **87%** of BERT-base STS (with STS12 win)
+- **89%** of BERT-base clustering (ARI)
+- **98%** of BERT-base retrieval (MRR)
+
+## Usage
+
+### Sentence-Transformers (Recommended)
+
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer('mjbommar/ogbert-2m-sentence')
+embeddings = model.encode(['your text here'])  # L2 normalized by default
+```
+
+### Direct Transformers Usage
+
+```python
+from transformers import AutoModel, AutoTokenizer
+import torch.nn.functional as F
+
+tokenizer = AutoTokenizer.from_pretrained('mjbommar/ogbert-2m-sentence')
+model = AutoModel.from_pretrained('mjbommar/ogbert-2m-sentence')
+
+inputs = tokenizer('your text here', return_tensors='pt', padding=True, truncation=True)
+outputs = model(**inputs)
+
+# Mean pooling + L2 normalize (critical for performance)
+mask = inputs['attention_mask'].unsqueeze(-1)
+pooled = (outputs.last_hidden_state * mask).sum(1) / mask.sum(1)
+embeddings = F.normalize(pooled, p=2, dim=1)
+```
+
+### For Fill-Mask Tasks
+
+Use [mjbommar/ogbert-2m-base](https://huggingface.co/mjbommar/ogbert-2m-base) instead.
+
+## Citation
+
+Forthcoming research. Contact authors for details.
+
+## License
+
+Apache 2.0

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "mjbommar/ogbert-2m-sentence",
+  "architectures": [
+    "ModernBertModel"
+  ],
+  "model_type": "modernbert",
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "cls_token_id": 4,
+  "eos_token_id": 1,
+  "sep_token_id": 5,
+  "pad_token_id": 2,
+  "unk_token_id": 3,
+  "mask_token_id": 6,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "cls",
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "dtype": "float32",
+  "embedding_dropout": 0.0,
+  "global_attn_every_n_layers": 3,
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu",
+  "hidden_size": 128,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "layer_norm_eps": 1e-05,
+  "layer_types": [
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "local_attention": 128,
+  "max_position_embeddings": 1024,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "repad_logits_with_grad": false,
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 160000.0,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "vocab_size": 8192
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f421c31ba05f45bbe8955d6122b7f2c3f773105cbe4f9549e28f915a835edef4
+size 8494856

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<|start|>",
+  "cls_token": "<|cls|>",
+  "eos_token": "<|end|>",
+  "mask_token": "<|mask|>",
+  "pad_token": "<|pad|>",
+  "sep_token": "<|sep|>",
+  "unk_token": "<|unk|>"
+}

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "additional_special_tokens": null,
+  "backend": "tokenizers",
+  "bos_token": "<|start|>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<|cls|>",
+  "eos_token": "<|end|>",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "mask_token": "<|mask|>",
+  "model_max_length": 1024,
+  "model_type": "modernbert",
+  "pad_token": "<|pad|>",
+  "sep_token": "<|sep|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|unk|>",
+  "vocab_size": 8191
+}