Add new LinkTransformer model.

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,82 @@
+---
+pipeline_tag: text-classification
+language: 
+- multilingual
+tags:
+- linktransformer
+- transformers
+- text-classification
+- tabular-classification
+
+---
+
+# 96abhishekarora/kn-eng-prop-m-nm
+
+This model is part of the [LinkTransformer](https://linktransformer.github.io/) ecosystem. While rooted in the a standard HuggingFace Transformer, this specific instance is tailored for text classification tasks. It classifies input sentences or paragraphs into specific categories or labels, leveraging the power of transformer architectures.
+
+The base model for this classifier is: bert. It is pretrained for the language: - multilingual.
+
+Labels are mapped to integers as follows: 
+
+{LABEL_MAP}
+
+For best results, append ಆಸ್ತಿ ಮಾಲೀಕನ ಹೆಸರು to the name
+
+## Usage with LinkTransformer
+
+After installing [LinkTransformer](https://linktransformer.github.io/):
+
+```python
+pip install -U linktransformer
+```
+
+Employ the model for text classification tasks:
+
+```python
+import linktransformer as lt
+df_clf_output = lt.classify_rows(df, on=["col_of_interest"], model="96abhishekarora/kn-eng-prop-m-nm")
+```
+
+
+## Training
+
+### Training your own LinkTransformer Classification Model
+
+With the provided tools, you can train a custom classification model:
+
+```python
+from linktransformer import train_clf_model
+
+best_model_path, best_metric, label_map = train_clf_model(
+    data="path_to_dataset.csv",
+    model="you-model-path-or-name",
+    on=["col_of_interest"],
+    label_col_name="label_column_name",
+    lr=5e-5,
+    batch_size=16,
+    epochs=3
+)
+```
+
+
+
+
+
+## Evaluation Results
+
+<!--- Describe how your model was evaluated -->
+
+Evaluation is typically based on metrics like accuracy, F1-score, precision, and recall.
+
+## Citing & Authors
+
+```
+@misc{arora2023linktransformer,
+                  title={LinkTransformer: A Unified Package for Record Linkage with Transformer Language Models},
+                  author={Abhishek Arora and Melissa Dell},
+                  year={2023},
+                  eprint={2309.00789},
+                  archivePrefix={arXiv},
+                  primaryClass={cs.CL}
+}
+```

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/mnt/122a7683-fa4b-45dd-9f13-b18cc4f4a187/deeprecordlinkage/linktransformer/extra_data/checkpoint-6520",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9c26fbf0b7a418c9766d87827a5ce69abe91d8bad0d230dd49986e6c178dec8
+size 711443456

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "extra_special_tokens": {},
+  "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]"
+}