Lamini T5 738M

🚀 LaMini-T5-738M

LaMini-T5-738M is a fine - tuned model in the LaMini - LM series, designed for text - to - text generation tasks, offering high - quality responses to natural language instructions.

🚀 Quick Start

This model is one of our LaMini - LM model series presented in the paper "[LaMini - LM: A Diverse Herd of Distilled Models from Large - Scale Instructions](https://github.com/mbzuai - nlp/lamini - lm)". It is a fine - tuned version of [t5 - large](https://huggingface.co/t5 - large) on the [LaMini - instruction dataset](https://huggingface.co/datasets/MBZUAI/LaMini - instruction), which contains 2.58M samples for instruction fine - tuning. For more details about our dataset, please visit our [project repository](https://github.com/mbzuai - nlp/lamini - lm/).

You can view other models in the LaMini - LM series below. Models marked with ✩ have the best overall performance given their size/architecture, and we recommend using them. More details can be found in our paper.

✨ Features

• Instruction - following: Designed to effectively respond to human instructions written in natural language.
• Fine - tuned: Based on [t5 - large](https://huggingface.co/t5 - large) and fine - tuned on a large - scale instruction dataset.

💻 Usage Examples

Basic Usage

# pip install -q transformers
from transformers import pipeline

checkpoint = "{model_name}"

model = pipeline('text2text-generation', model = checkpoint)

input_prompt = 'Please let me know your thoughts on the given place and why you think it deserves to be visited: \n"Barcelona, Spain"'
generated_text = model(input_prompt, max_length=512, do_sample=True)[0]['generated_text']

print("Response", generated_text)

🔧 Technical Details

Training Procedure

We initialize with [t5 - large](https://huggingface.co/t5 - large) and fine - tune it on our [LaMini - instruction dataset](https://huggingface.co/datasets/MBZUAI/LaMini - instruction). The model has a total of 738M parameters.

Training Hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0005
• train_batch_size: 128
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 512
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• num_epochs: 5

📚 Documentation

Evaluation

We conducted two sets of evaluations: automatic evaluation on downstream NLP tasks and human evaluation on user - oriented instructions. For more details, please refer to our paper.

Limitations

More information needed

📄 License

This model is released under the [CC By NC 4.0](https://creativecommons.org/licenses/by - nc/4.0/) license.

📖 Citation

@article{lamini-lm,
  author       = {Minghao Wu and
                  Abdul Waheed and
                  Chiyu Zhang and
                  Muhammad Abdul-Mageed and
                  Alham Fikri Aji
                  },
  title        = {LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions},
  journal      = {CoRR},
  volume       = {abs/2304.14402},
  year         = {2023},
  url          = {https://arxiv.org/abs/2304.14402},
  eprinttype   = {arXiv},
  eprint       = {2304.14402}
}