README.md

---
base_model: gpt2
library_name: peft
datasets:
- clemsadand/quote_data
metrics:
- bertscore
---

# Model Card for Quote Generator

<!-- Provide a quick summary of what the model is/does. -->

This model is a fine-tuned version of GPT-2 using LoRA (Low-Rank Adaptation) to generate quotes based on a custom dataset. It is designed to create meaningful and inspirational quotes.

## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->

The Quote Generator is built on top of the GPT-2 model, fine-tuned using the Low-Rank Adaptation (LoRA) technique to specialize in generating quotes. The training dataset comprises a curated collection of quotes from various sources, enabling the model to produce high-quality and contextually relevant quotes.

- **Developed by:** Clément Adandé
<!-- - **Funded by [optional]:** N/A -->
<!-- - **Shared by [optional]:** Clément Adandé -->
- **Model type:** Language Model (NLP)
- **Language(s) (NLP):** English
- **License:** MIT
- **Finetuned from model :** GPT-2

### Model Sources

<!-- Provide the basic links for the model. -->

- **Repository:** [Quote Generator](https://huggingface.co/clemsadand/quote_generator/)
<!-- - **Paper [optional]:** N/A -->
- **Demo :** [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1SfCQkGIz5EyGODEYD-i4OggG4gM-Qx9t?usp=sharing)

## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

### Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

The model can be directly used to generate quotes for various applications, such as social media content, motivational messages, and creative writing.

### Downstream Use

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

The model can be further fine-tuned for specific contexts or integrated into applications requiring quote generation.

### Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

The model should not be used for generating harmful, offensive, or misleading content. It may not perform well for generating quotes in languages other than English.

## Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

The model may inherit biases present in the training data. Generated quotes may not always be factually accurate or appropriate for all contexts. Users should verify the content before use in sensitive applications.

### Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases, and limitations of the model. It is recommended to review and edit the generated quotes before public use.

## How to Get Started with the Model

Use the code below to get started with the model.

```python
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer

config = PeftConfig.from_pretrained("clemsadand/quote_generator")
base_model = AutoModelForCausalLM.from_pretrained("gpt2")
model = PeftModel.from_pretrained(base_model, "clemsadand/quote_generator")

tokenizer = AutoTokenizer.from_pretrained("gpt2")

def generate_quote(input_text):
    input_tensor = tokenizer(input_text, return_tensors="pt")
    output = model.generate(input_tensor["input_ids"], attention_mask=input_tensor["attention_mask"],
                          max_length=64, num_beams=5, no_repeat_ngram_size=2,
                          early_stopping=True, pad_token_id=tokenizer.eos_token_id, do_sample=True, temperature=0.7)
    output = tokenizer.decode(output[0], ski_special_tokens=True, clean_up_tokenization_spaces=True)
    return output

input_text = "Generate a quote about kindness with the keywords compassion, empathy, help, generosity, care"

print(generate_quote(input_text))