Upload 8 files

README.md

@@ -0,0 +1,123 @@
+# RoBERTa-Base Model for Named Entity Recognition (NER) on CoNLL-2003 Dataset
+
+This repository hosts a fine-tuned version of the RoBERTa model for Named Entity Recognition (NER) using the CoNLL-2003 dataset. The model is capable of identifying and classifying named entities such as people, organizations, locations, etc.
+
+## Model Details
+
+- **Model Architecture:** RoBERTa Base  
+- **Task:** Named Entity Recognition  
+- **Dataset:** CoNLL-2003 (Hugging Face Datasets)  
+- **Quantization:** Float16
+- **Fine-tuning Framework:** Hugging Face Transformers  
+
+---
+
+## Installation
+
+```bash
+pip install datasets transformers seqeval torch --quiet
+```
+
+---
+
+## Loading the Model
+
+
+```python
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+import torch
+
+# Load tokenizer and model
+model = "roberta-base"
+tokenizer = AutoTokenizer.from_pretrained(model)
+model = AutoModelForSequenceClassification.from_pretrained(model)
+# Define test sentences
+sentences = [
+    "Barack Obama was born in Hawaii.",
+    "Elon Musk founded SpaceX and Tesla.",
+    "Apple is headquartered in Cupertino, California."
+]
+
+for sentence in sentences:
+    tokens = tokenizer(sentence, return_tensors="pt", truncation=True, is_split_into_words=False).to(device)
+    with torch.no_grad():
+        outputs = model(**tokens)
+        logits = outputs.logits
+        predictions = torch.argmax(logits, dim=2)
+    predicted_labels = predictions[0].cpu().numpy()
+    tokens_decoded = tokenizer.convert_ids_to_tokens(tokens["input_ids"][0])
+    print(f"Sentence: {sentence}")
+    for token, label_id in zip(tokens_decoded, predicted_labels):
+        label = label_list[label_id]
+        if token.startswith("Ġ") or not token.startswith("▁"):
+            token = token.replace("Ġ", "")
+        if label != "O":
+            print(f"{token}: {label}")
+    print("\n" + "-"*50 + "\n")
+```
+
+
+## Performance Metrics
+
+- **Accuracy:** 0.9921  
+- **Precision:** 0.9466
+- **Recall:** 0.9589	  
+- **F1 Score:** 0.9527  
+
+---
+
+## Fine-Tuning Details
+
+### Dataset
+
+The dataset used is the CoNLL-2003 dataset, which contains labeled tokens for Named Entity Recognition (NER).
+Entities are categorized into classes such as PER (person), ORG (organization), LOC (location), and MISC (miscellaneous).
+It includes four columns: the word, part-of-speech tag, syntactic chunk tag, and NER tag.
+
+The dataset is automatically loaded using the Hugging Face datasets library and is split into train, validation, and test sets.
+
+
+### Training
+
+- **Epochs:** 3 
+- **Batch size:** 16 (train) / 16 (eval)  
+- **Learning rate:** 2e-5  
+- **Evaluation strategy:** `epoch`  
+- **FP16 Training:** Enabled  
+- **Trainer:** Hugging Face `Trainer` API  
+
+---
+
+## Quantization
+
+Post-training quantization was applied using `model.to(dtype=torch.float16)` to reduce model size and speed up inference.
+
+---
+
+## Repository Structure
+
+```bash
+.
+├── quantized-model/                            # Directory containing trained model artifacts
+│   ├── config.json
+│   ├── merges.txt
+│   ├── model.safetensors            # (May appear as 'model' in UI)
+│   ├── special_tokens_map.json
+│   ├── tokenizer.json
+│   ├── tokenizer_config.json
+│   └── vocab.json
+├── README.md
+```
+
+---
+
+## Limitations
+
+- The model is trained only on CoNLL-2003 and may not generalize to unseen NER tasks.
+- Token misalignment may occur for complex or ambiguous phrases.
+
+
+## Contributing
+
+Feel free to open issues or submit pull requests to improve the model, training process, or documentation.
+

config.json

@@ -0,0 +1,48 @@
+{
+  "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": "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"
+  },
+  "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
+  },
+  "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 sha256:490ea47e40c26ba0cd15162c39a18f2a06f2030837bbcb40b1aab60966ca19c3
+size 248147794

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}