Upload 8 files

README.md

@@ -0,0 +1,126 @@
+# RoBERTa-Base Quantized Model for Sentiment Analysis
+
+This repository hosts a quantized version of the RoBERTa model, fine-tuned for sentiment-analysis-classification tasks. The model has been optimized for efficient deployment while maintaining high accuracy, making it suitable for resource-constrained environments.
+
+## Model Details
+ 
+- **Model Architecture:** RoBERTa Base   
+- **Task:** Sentiment Analysis
+- **Dataset:** Custom Twitter Dataset (`twitter_training.csv`)
+- **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")
+ 
+# Define a test sentence
+
+test_sentence = "The food was absolutely delicious and the service was amazing!"
+ 
+# Tokenize input
+
+inputs = tokenizer(test_sentence, return_tensors="pt", padding=True, truncation=True, max_length=128)
+ 
+# Ensure input tensors are in correct dtype
+
+inputs["input_ids"] = inputs["input_ids"].long()  # Convert to long type
+
+inputs["attention_mask"] = inputs["attention_mask"].long()  # Convert to long type
+
+# Move inputs to the model's device
+
+inputs = {key: value.to(device) for key, value in inputs.items()}
+ 
+# Make prediction
+
+with torch.no_grad():
+
+    outputs = quantized_model(**inputs)
+ 
+# Get predicted class
+
+predicted_class = torch.argmax(outputs.logits, dim=1).item()
+
+print(f"Predicted Class: {predicted_class}")
+ 
+ 
+label_mapping = {0: "very_negative", 1: "nagative", 2: "neutral", 3: "Positive", 4: "very_positive"}   
+
+#Example
+ 
+predicted_label = label_mapping[predicted_class]
+
+print(f"Predicted Label: {predicted_label}")
+ 
+```
+ 
+## Performance Metrics
+ 
+- **Accuracy:** 0.82
+ 
+## Fine-Tuning Details
+ 
+### Dataset
+ 
+The dataset is taken from Kaggle .
+ 
+### Training
+ 
+- Number of epochs: 3  
+
+- Batch size: 8  
+
+- Evaluation strategy: epoch  
+
+- Learning rate: 2e-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
+ 
+```
+
+.
+
+├── model/               # Contains the quantized model files
+
+├── tokenizer_config/    # Tokenizer configuration and vocabulary files
+
+├── model.safensors/     # 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 +1,37 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "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:f04bd6d7a794f774ac3341c4994b77a1287acd11fa9105ca4586a35a1c1f1bba
+size 249319966

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": false,
+  "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>"
+}