first commit

.gitattributes

@@ -1,35 +1 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
 *.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,103 @@
+---
+language:
+- en
+tags:
+- fill-mask
+- masked-lm
+- feature-extraction
+- semantic-similarity
+- historical-text
+- newspapers
+license: mit
+pipeline_tag: fill-mask
+---
+
+# NewsBERT
+
+**NewsBERT** is a domain-adapted masked language model based on [`google-bert/bert-base-uncased`](https://huggingface.co/google-bert/bert-base-uncased). It has been fine-tuned with a **masked language modeling (MLM)** objective on all **historical English newspaper text** from the following two collections:
+- [HMD14](https://bl.iro.bl.uk/concern/datasets/2800eb7d-8b49-4398-a6e9-c2c5692a1304)
+- [LwM](https://bl.iro.bl.uk/concern/datasets/99dc570a-9460-48ac-baed-9d2b8c4c13c0?locale=en)
+
+NewsBERT retains the architecture and vocabulary of BERT-base (uncased), with only weights being adapted to these datasets.
+
+---
+
+## Model Details
+
+- **Model type:** `BertForMaskedLM`
+- **Base model:** `google-bert/bert-base-uncased`
+- **Vocabulary:** WordPiece (30,522 tokens)
+- **Hidden size:** 768  
+- **Layers:** 12  
+- **Heads:** 12  
+- **Max sequence length:** 512  
+- **Fine-tuning objective:** Masked language modeling (MLM)
+
+---
+
+## How to Use
+
+### 1. **Fill-Mask Pipeline**
+
+```python
+from transformers import AutoTokenizer, AutoModelForMaskedLM, pipeline
+
+model_id = "npedrazzini/NewsBERT"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForMaskedLM.from_pretrained(model_id)
+
+fill_mask = pipeline("fill-mask", model=model, tokenizer=tokenizer)
+
+text = "The [MASK] was published in the newspaper."
+preds = fill_mask(text)
+
+for p in preds:
+    print(f"{p['sequence']} (score={p['score']:.4f})")
+
+```
+
+### 2. Use as an Encoder (CLS Embeddings)
+
+```
+import torch
+from transformers import AutoTokenizer, AutoModel
+
+model_id = "npedrazzini/NewsBERT"
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModel.from_pretrained(model_id).to(device)
+model.eval()
+
+def encode(text, max_length=512):
+    inputs = tokenizer(
+        text,
+        return_tensors="pt",
+        truncation=True,
+        max_length=max_length
+    ).to(device)
+
+    with torch.no_grad():
+        outputs = model(**inputs)
+        embedding = outputs.last_hidden_state[:, 0, :]  # CLS token
+
+    return embedding.squeeze(0).cpu()  # [768]
+
+embedding = encode("Example newspaper article text...")
+print(embedding.shape)  # torch.Size([768])
+```
+
+
+### 3. Compute Similarity Between Two Articles
+
+```
+import torch.nn.functional as F
+
+e1 = encode("Article text one...")
+e2 = encode("Another article...")
+
+cos_sim = F.cosine_similarity(e1, e2, dim=0)
+print("Cosine similarity:", cos_sim.item())
+```
+

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.45.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60ba0440fa6bd1c15b10c269ad99957b11fc7a4af90a60461a64a137d1ed8d61
+size 438080896

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 +1,55 @@
+{
+  "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_lower_case": true,
+  "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]"
+}