---
license: cc-by-nc-4.0
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. -->

<p align="center" width="100%">
    <a><img src="https://raw.githubusercontent.com/mbzuai-nlp/lamini-lm/main/images/lamini.png" alt="Title" style="width: 100%; min-width: 300px; display: block; margin: auto;"></a>
</p>

# LaMini-Flan-T5-248M

[![Model License](https://img.shields.io/badge/Model%20License-CC%20By%20NC%204.0-red.svg)]()

This model is one of our LaMini-LM model series in paper "[LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions](https://github.com/mbzuai-nlp/lamini-lm)". This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on [LaMini-instruction dataset](https://huggingface.co/datasets/MBZUAI/LaMini-instruction) 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-lm/).  
You can view other models of LaMini-LM series as follows. Models with ✩ are those with the best overall performance given their size/architecture, hence we recommend using them. More details can be seen in our paper. 


## Use

### Intended use
We recommend using the model to response to human instructions written in natural language. 

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

```python
# 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)
```

## Training Procedure

<p align="center" width="100%">
    <a><img src="https://raw.githubusercontent.com/mbzuai-nlp/lamini-lm/main/images/lamini-pipeline.drawio.png" alt="Title" style="width: 100%; min-width: 250px; display: block; margin: auto;"></a>
</p>

We initialize with [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) and fine-tune it on our [LaMini-instruction dataset](https://huggingface.co/datasets/MBZUAI/LaMini-instruction). Its total number of parameters is 248M. 

### 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