Upload folder using huggingface_hub

README.md

@@ -0,0 +1,54 @@
+
+# Model Name: Your Model's Name
+
+## Model Description
+This model is a **Named Entity Recognition (NER)** model fine-tuned on the **CoNLL-03** dataset. It is designed to recognize **person**, **organization**, and **location** entities in English text. The model is based on the **BERT architecture** and is useful for information extraction tasks, such as named entity recognition in documents, web scraping, or chatbots.
+
+### Model Architecture
+- **Architecture**: BERT-based model for token classification
+- **Pre-trained Model**: BERT
+- **Fine-tuning Dataset**: CoNLL-03
+- **Languages**: English
+
+## Intended Use
+This model is designed for Named Entity Recognition tasks. It can identify and classify entities such as:
+- **Person**: People’s names (e.g., "Elon Musk")
+- **Organization**: Company or organization names (e.g., "Tesla", "Bank of America")
+- **Location**: Geographical locations (e.g., "New York", "Paris")
+
+### Use Cases
+- **Document classification**: Classifying text into named entity categories.
+- **Information extraction**: Extracting entities from a large corpus of text.
+- **Chatbots**: Enhance chatbots by identifying named entities within user queries.
+- **Named entity linking**: Link entities to a knowledge base.
+
+## How to Use
+To use the model, you need to load the tokenizer and model with the `transformers` library. Here's an example of how to do that:
+
+```python
+from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
+
+# Load the tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained("your-username/your-model-name")
+model = AutoModelForTokenClassification.from_pretrained("your-username/your-model-name")
+
+# Initialize the NER pipeline
+ner_pipeline = pipeline("ner", model=model, tokenizer=tokenizer)
+
+# Use the model to predict named entities in a text
+result = ner_pipeline("Elon Musk is the CEO of Tesla and lives in California.")
+print(result)
+
+# Model Training Data
+This model was trained on the CoNLL-03 dataset, which contains English text annotated with named entity labels. The dataset consists of:
+
+Training set: 14,041 sentences
+Validation set: 3,466 sentences
+Test set: 3,684 sentences
+The entities are labeled into three categories: Person, Organization, and Location.
+
+# Preprocessing Steps
+Tokenization using the BERT tokenizer.
+Alignment of labels with tokenized inputs (considering word-piece tokens).
+Padding and truncating sentences to a fixed length for uniformity.
+

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "/kaggle/working/NER",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 64000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def59075e66a0fc9a86dc5c4af391bb89a1811dcff58bf73829897a280832756
+size 538465128

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 +1,86 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[رابط]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "6": {
+      "content": "[بريد]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "7": {
+      "content": "[مستخدم]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": [
+    "[بريد]",
+    "[مستخدم]",
+    "[رابط]"
+  ],
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}