---
license: apache-2.0
tags:
- generated_from_trainer
- instruction fine-tuning
model-index:
- name: flan-t5-small-distil-v2
  results: []
language:
- en
pipeline_tag: text2text-generation
widget:
  - text: >-
      how can I become more healthy?
    example_title: example
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# LaMini-FLAN-T5-77M

[![Code License](https://img.shields.io/badge/Code%20License-Apache_2.0-green.svg)](https://github.com/tatsu-lab/stanford_alpaca/blob/main/LICENSE)
[![Data License](https://img.shields.io/badge/Data%20License-CC%20By%20NC%204.0-red.svg)](https://github.com/tatsu-lab/stanford_alpaca/blob/main/DATA_LICENSE)

This model is one of our LaMini model series in paper "[LaMini: A Diverse Herd of Distilled Models from Large-Scale Instructions]()". This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on [LaMini dataset]() that 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/).  
You can view other LaMini model series as follow. Note that not all models are performing as well. More details can be seen in our paper. 

<table>
<thead>
  <tr>
    <th>Base model</th>
    <th colspan="4">LaMini series (#parameters)</th>
  </tr>
</thead>
<tbody>
  <tr>
    <td>T5</td>
    <td>LaMini-T5-61M</td>
    <td>LaMini-T5-223M</td>
    <td>LaMini-T5-738M</td>
    <td></td>
  </tr>
   <tr>
        <td>Flan-T5</td>
        <td>LaMini-Flan-T5-77M</td>
        <td>LaMini-Flan-T5-248M</td>
        <td>LaMini-Flan-T5-783M</td>
    <td></td>
  </tr>
    <tr>
    <td>Cerebras-GPT</td>
    <td>LaMini-Cerebras-111M</td>
    <td>LaMini-Cerebras-256M</td>
    <td>LaMini-Cerebras-590M</td>
    <td>LaMini-Cerebras-1.3B</td>
  </tr>
  <tr>
    <td>GPT-2</td>
    <td><a href="https://huggingface.co/MBZUAI/lamini-gpt-124m" target="_blank" rel="noopener noreferrer">LaMini-GPT-124M</a></td>
    <td><a href="https://huggingface.co/MBZUAI/lamini-gpt-774m" target="_blank" rel="noopener noreferrer">LaMini-GPT-774M</a></td>
    <td><a href="https://huggingface.co/MBZUAI/lamini-gpt-1.5b" target="_blank" rel="noopener noreferrer">LaMini-GPT-1.5B</a></td>
    <td></td>
  </tr>
  <tr>
    <td>GPT-Neo</td>
    <td>LaMini-Neo-125M</td>
    <td>LaMini-Neo-1.3B</td>
    <td></td>
    <td></td>
  </tr>
  <tr>
    <td>GPT-J</td>
    <td colspan="4">coming soon</td>
  </tr>
  <tr>
    <td>LLaMA</td>
    <td colspan="4">coming soon</td>
  </tr>

  
</tbody>
</table>


## Use

### Intended use
We recommend to use model to reponse to human instructions wrote in natural language. 

We now show you how to load and use our model using HuggingFace `pipline()`. 

```python
# pip install -q transformers
from transformers import pipeline

checkpoint = "{model_name}"

model = pipeline('text2text-generation', model=checkpoint, use_auth_token=True, device=0)

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

print("Response": generated_text)
```

## Training Procedure
We initialize with [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) and fine-tune it on our [LaMini dataset](). Its total number of parameters is 61M. 

### 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

## Evaluation
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](). 

## Limitations

More information needed


# Citation
```bibtex
@misc{,
      title={LaMini: Distilling Knowledge from Large Language Models}, 
      author={},
      year={2023},
      eprint={},
      archivePrefix={},
      primaryClass={}
}
```