Add model

README.md

@@ -0,0 +1,26 @@
+---
+language: en
+license: apache-2.0
+---
+
+# SportsBERT Small
+
+This is a `22.7M` parameter [BERT](https://arxiv.org/abs/1810.04805) encoder-only model trained on [Wikipedia articles](https://huggingface.co/datasets/NeuML/wikipedia-20260401) labeled as `sports` related.
+
+This is a domain-specialized small model that often performs as good as models 10-100x larger. It demonstrates that narrowing down a model to a small domain requires less overall parameters than models generalized for all problems.
+
+## Usage
+
+`sportsbert-small` can be loaded using [Hugging Face Transformers](https://huggingface.co/docs/transformers/en/index) as follows.
+
+```python
+from transformers import AutoModel
+
+model = AutoModel.from_pretrained("neuml/sportsbert-small")
+```
+
+The model is intended to be further fine-tuned for a specific task such as Text Classification, Entity Extraction, Sentence Embeddings and so on.
+
+## More Information
+
+Read more about the model in [this article](https://hf.co/blog/NeuML/sportsbert-small).

config.json

@@ -0,0 +1,28 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.11.0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b980f3e17217a457db9a5712c5fa51280b47e0f21537530236aef79c19d6cb95
+size 90990200

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a295b6724460051f02042e4a08ca9f3a0b216918a0524fed1f5b8190dd4bfaab
+size 5137