philipp-zettl/t5-small-paraphraser (Quantized)

Description

This model is a quantized version of the original model philipp-zettl/t5-small-paraphraser.

It's quantized using the TorchAO library using the torchao-my-repo space.

Quantization Details

• Quantization Type: Int4WeightOnly
• Group Size: 128

📄 Original Model Information

Model Card for Model ID

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

• Developed by: [More Information Needed]
• Funded by [optional]: [More Information Needed]
• Shared by [optional]: [More Information Needed]
• Model type: [More Information Needed]
• Language(s) (NLP): [More Information Needed]
• License: [More Information Needed]
• Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

• Repository: [More Information Needed]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

model_name = 'philipp-zettl/t5-small-long-qa'
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained('google/flan-t5-small')

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = model.to(device)

def eval(inputs, tokenizer, model):
    model_inputs = tokenizer(inputs, max_length=512, padding=True, truncation=True)
    input_ids = torch.tensor(model_inputs['input_ids']).to(device)
    attention_mask = torch.tensor(model_inputs['attention_mask']).to(device)
    with torch.no_grad():
        sample_output = model.generate(
            input_ids[:1],
            max_length=85,
            temperature=0.5,
            do_sample=True
        )
        sample_output_text = tokenizer.decode(sample_output[0], skip_special_tokens=True)
        input_text = tokenizer.decode(input_ids[0], skip_special_tokens=True)
        print(f"Sample Input:\n \"{input_text}\"\n\n")
        print(f"Model Output: \"{sample_output_text}\"")


statement = "The model should change the words but not the meaning of this sentence."
eval([f"paraphrase: {statement} . output: "], tokenizer, model)

Training Details

Training Data

For training we used the grammarly/medit dataset, filtered by german/english paraphrasing samples.

Training Procedure

Preprocessing [optional]

def preprocess_batch(batch, tokenizer, max_input_length=512, max_output_length=128):
    questions = batch['src']
    answers = batch['tgt']

    inputs = [f"paraphrase: {q} output: " for q in questions]
    model_inputs = tokenizer(inputs, max_length=max_input_length, padding=True, truncation=True)

    labels = tokenizer(answers, max_length=max_output_length, padding=True, truncation=True)
    model_inputs['labels'] = labels['input_ids']

    return model_inputs

# Tokenize the dataset
train_dataset = train_dataset.filter(lambda x: x['task'] == 'paraphrasing' and x['lang'] in ['de', 'en']).map(lambda batch: preprocess_batch(batch, tokenizer), batched=True)
validation_dataset = validation_dataset.filter(lambda x: x['task'] == 'paraphrasing' and x['lang'] in ['de', 'en']).map(lambda batch: preprocess_batch(batch, tokenizer), batched=True)

# Set format for PyTorch
train_dataset.set_format(type='torch', columns=['input_ids', 'attention_mask', 'labels'])
validation_dataset.set_format(type='torch', columns=['input_ids', 'attention_mask', 'labels'])

Training Hyperparameters

• Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: [More Information Needed]
• Hours used: 9.83 hr
• Cloud Provider: -
• Compute Region: eu-central-1
• Carbon Emitted:

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]