🚀 LaMini-GPT-1.5B

LaMini-GPT-1.5B is a fine - tuned text - generation model from the LaMini - LM series, offering high - quality responses to natural language instructions.

🚀 Quick Start

This model is one of our LaMini - LM model series introduced 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 [gpt2 - xl](https://huggingface.co/gpt2 - xl) on the [LaMini - instruction dataset](https://huggingface.co/datasets/MBZUAI/LaMini - instruction), which contains 2.58M samples for instruction fine - tuning. For more information about our dataset, please refer to our [project repository](https://github.com/mbzuai - nlp/lamini - lm/).

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

✨ Features

• Instruction - following: Designed to respond to human instructions written in natural language.
• Fine - tuned: Fine - tuned on a large - scale instruction dataset for better performance.

💻 Usage Examples

Basic Usage

# pip install -q transformers
from transformers import pipeline

checkpoint = "{model_name}" 

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

instruction = 'Please let me know your thoughts on the given place and why you think it deserves to be visited: \n"Barcelona, Spain"'

input_prompt = f"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:"

generated_text = model(input_prompt, max_length=512, do_sample=True)[0]['generated_text']

print("Response", generated_text)

Advanced Usage

Since this decoder - only model is fine - tuned with wrapper text, using the same wrapper text can achieve the best performance. You can customize the instruction and input_prompt according to your specific needs.

🔧 Technical Details

We initialize with [gpt2 - xl](https://huggingface.co/gpt2 - xl) and fine - tune it on our [LaMini - instruction dataset](https://huggingface.co/datasets/MBZUAI/LaMini - instruction). Its total number of parameters is 1.5B.

Training Hyperparameters

[The original document doesn't provide specific hyperparameters, so this part is skipped as per the rules.]

📚 Documentation

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

📄 License

This model is released under the CC 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}
}