Upload 9 files

README.md

@@ -0,0 +1,109 @@
+# RoBERTa-Base Quantized Model for Named Entity Recognition (NER)
+
+This repository contains a quantized version of the RoBERTa model fine-tuned for Named Entity Recognition (NER) on the WikiANN (English) dataset. The model is particularly suitable for **tagging named entities in news articles**, such as persons, organizations, and locations. It has been optimized for efficient deployment using quantization techniques.
+
+
+## Model Details
+ 
+- **Model Architecture:** RoBERTa Base   
+- **Task:** Named Entity Recognition 
+- **Dataset:** WikiANN (English)
+- **Use Case:** Tagging news articles with named entities  
+- **Quantization:** Float16  
+- **Fine-tuning Framework:** Hugging Face Transformers  
+
+## Usage
+ 
+### Installation
+ 
+```sh
+pip install transformers torch
+```
+ 
+ 
+### Loading the Model
+ 
+```python
+ 
+from transformers import RobertaTokenizerFast, RobertaForSequenceClassification, Trainer, TrainingArguments
+import torch
+
+
+ 
+# Load tokenizer
+
+tokenizer = RobertaTokenizerFast.from_pretrained("roberta-base")
+ 
+# Create NER pipeline
+ner_pipeline = pipeline(
+    "ner",
+    model=model,
+    tokenizer=tokenizer,
+    aggregation_strategy="simple"
+)
+
+# Sample news headline
+text = "Apple Inc. is planning to open a new campus in London by the end of 2025."
+
+# Inference
+entities = ner_pipeline(text)
+
+# Display results
+for ent in entities:
+    print(f"{ent['word']}: {ent['entity_group']} ({ent['score']:.2f})")
+
+```
+ 
+## Performance Metrics
+ 
+- **Accuracy:** 0.923422	
+- **Precision:** 0.923052	
+- **Recall:** 0.923422
+- **F1:** 0.923150
+
+ 
+## Fine-Tuning Details
+ 
+### Dataset
+ 
+The dataset is taken from Hugging Face WikiANN (English).
+ 
+### Training
+ 
+- Number of epochs: 5  
+
+- Batch size: 16
+
+- Evaluation strategy: epoch  
+
+- Learning rate: 3e-5  
+ 
+### Quantization
+ 
+Post-training quantization was applied using PyTorch's built-in quantization framework to reduce the model size and improve inference efficiency.
+ 
+## Repository Structure
+ 
+```
+
+.
+├── config.json
+├── tokenizer_config.json    
+├── sepcial_tokens_map.json 
+├── tokenizer.json        
+├── model.safetensors    # Fine Tuned Model
+├── README.md            # Model documentation
+
+```
+ 
+## Limitations
+ 
+- The model may not generalize well to domains outside the fine-tuning dataset.  
+
+- Quantization may result in minor accuracy degradation compared to full-precision models.  
+ 
+## Contributing
+ 
+Contributions are welcome! Feel free to open an issue or submit a pull request if you have suggestions or improvements.
+
+ 

config.json

@@ -0,0 +1,44 @@
+{
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 5,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float16",
+  "transformers_version": "4.51.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db5e9cfb52d845e0f66a72a18c1a0efeae654aa7f13c7f96505c67e072e02e6f
+size 248144718

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48332ab964fedff29c76d05ee53d1996b9b3fbd342c84a6e69dfa676f563312c
+size 5240