Mujahid8065/vroberta-regression

Regression Model

A fine-tuned RoBERTa model for sequence classification with regression problem type.

Model Details

• Architecture: RobertaForSequenceClassification
• Model Type: RoBERTa
• Problem Type: Regression
• Base Model: RoBERTa
• Transformers Version: 4.51.3

Model Specifications

• Hidden Size: 768
• Number of Layers: 12
• Number of Attention Heads: 12
• Intermediate Size: 3072
• Max Position Embeddings: 514
• Vocabulary Size: 50,265
• Hidden Activation: GELU
• Dropout: 0.1 (attention and hidden layers)

Tokenizer

• Tokenizer Type: RobertaTokenizer
• Model Max Length: 512 tokens
• Special Tokens: <s>, </s>, <pad>, <unk>, <mask>

Files

• model.safetensors - Model weights in SafeTensors format
• config.json - Model configuration
• tokenizer.json - Tokenizer model file
• tokenizer_config.json - Tokenizer configuration
• vocab.json - Vocabulary file
• merges.txt - BPE merge rules
• special_tokens_map.json - Special tokens mapping
• training_args.bin - Training arguments (binary)

Usage

Installation

pip install transformers torch

Loading the Model

from transformers import RobertaForSequenceClassification, RobertaTokenizer
import torch

# Load tokenizer and model
tokenizer = RobertaTokenizer.from_pretrained("./")
model = RobertaForSequenceClassification.from_pretrained("./")

# Set model to evaluation mode
model.eval()

Inference Example

# Example text
text = "Your input text here"

# Tokenize input
inputs = tokenizer(
    text,
    return_tensors="pt",
    truncation=True,
    max_length=512,
    padding=True
)

# Get predictions
with torch.no_grad():
    outputs = model(**inputs)
    predictions = outputs.logits

# For regression, the output is a continuous value
predicted_value = predictions.item()
print(f"Predicted value: {predicted_value}")

Batch Inference

# Multiple texts
texts = ["Text 1", "Text 2", "Text 3"]

# Tokenize
inputs = tokenizer(
    texts,
    return_tensors="pt",
    truncation=True,
    max_length=512,
    padding=True
)

# Predict
with torch.no_grad():
    outputs = model(**inputs)
    predictions = outputs.logits

# Get predictions for each text
for i, text in enumerate(texts):
    print(f"Text: {text}")
    print(f"Predicted value: {predictions[i].item()}")

Notes

• This model is configured for regression tasks, meaning it outputs continuous values rather than discrete class labels
• The model accepts sequences up to 512 tokens in length
• Inputs longer than 512 tokens will be truncated
• The model uses SafeTensors format for efficient and safe model loading

Requirements

• Python 3.7+
• PyTorch
• Transformers >= 4.51.3
• safetensors (for loading model weights)

License

Please refer to the original RoBERTa model license and any additional terms specified for this fine-tuned model.