Commit
•
7a99dc7
1
Parent(s):
ffb2d16
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,157 +1,101 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: cc-by-nc-4.0
|
| 3 |
-
tags:
|
| 4 |
-
- generated_from_trainer
|
| 5 |
-
- instruction fine-tuning
|
| 6 |
-
model-index:
|
| 7 |
-
- name: flan-t5-small-distil-v2
|
| 8 |
-
results: []
|
| 9 |
-
language:
|
| 10 |
-
- en
|
| 11 |
-
pipeline_tag: text2text-generation
|
| 12 |
-
widget:
|
| 13 |
-
- text: >-
|
| 14 |
-
how can I become more healthy?
|
| 15 |
-
example_title: example
|
| 16 |
-
---
|
| 17 |
-
|
| 18 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 19 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 20 |
-
|
| 21 |
-
<p align="center" width="100%">
|
| 22 |
-
<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>
|
| 23 |
-
</p>
|
| 24 |
-
|
| 25 |
-
# LaMini-Flan-T5-248M
|
| 26 |
-
|
| 27 |
-
[]()
|
| 28 |
-
|
| 29 |
-
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/).
|
| 30 |
-
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.
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
<
|
| 58 |
-
|
| 59 |
-
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
|
| 93 |
-
|
| 94 |
-
|
| 95 |
-
|
| 96 |
-
|
| 97 |
-
|
| 98 |
-
|
| 99 |
-
|
| 100 |
-
|
| 101 |
-
|
| 102 |
-
model = pipeline('text2text-generation', model = checkpoint)
|
| 103 |
-
|
| 104 |
-
input_prompt = 'Please let me know your thoughts on the given place and why you think it deserves to be visited: \n"Barcelona, Spain"'
|
| 105 |
-
generated_text = model(input_prompt, max_length=512, do_sample=True)[0]['generated_text']
|
| 106 |
-
|
| 107 |
-
print("Response", generated_text)
|
| 108 |
-
```
|
| 109 |
-
|
| 110 |
-
## Training Procedure
|
| 111 |
-
|
| 112 |
-
<p align="center" width="100%">
|
| 113 |
-
<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>
|
| 114 |
-
</p>
|
| 115 |
-
|
| 116 |
-
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.
|
| 117 |
-
|
| 118 |
-
### Training Hyperparameters
|
| 119 |
-
|
| 120 |
-
The following hyperparameters were used during training:
|
| 121 |
-
- learning_rate: 0.0005
|
| 122 |
-
- train_batch_size: 128
|
| 123 |
-
- eval_batch_size: 64
|
| 124 |
-
- seed: 42
|
| 125 |
-
- gradient_accumulation_steps: 4
|
| 126 |
-
- total_train_batch_size: 512
|
| 127 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 128 |
-
- lr_scheduler_type: linear
|
| 129 |
-
- num_epochs: 5
|
| 130 |
-
|
| 131 |
-
## Evaluation
|
| 132 |
-
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]().
|
| 133 |
-
|
| 134 |
-
## Limitations
|
| 135 |
-
|
| 136 |
-
More information needed
|
| 137 |
-
|
| 138 |
-
|
| 139 |
-
# Citation
|
| 140 |
-
|
| 141 |
-
```bibtex
|
| 142 |
-
@article{lamini-lm,
|
| 143 |
-
author = {Minghao Wu and
|
| 144 |
-
Abdul Waheed and
|
| 145 |
-
Chiyu Zhang and
|
| 146 |
-
Muhammad Abdul-Mageed and
|
| 147 |
-
Alham Fikri Aji
|
| 148 |
-
},
|
| 149 |
-
title = {LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions},
|
| 150 |
-
journal = {CoRR},
|
| 151 |
-
volume = {abs/2304.14402},
|
| 152 |
-
year = {2023},
|
| 153 |
-
url = {https://arxiv.org/abs/2304.14402},
|
| 154 |
-
eprinttype = {arXiv},
|
| 155 |
-
eprint = {2304.14402}
|
| 156 |
-
}
|
| 157 |
```
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
- instruction fine-tuning
|
| 6 |
+
model-index:
|
| 7 |
+
- name: flan-t5-small-distil-v2
|
| 8 |
+
results: []
|
| 9 |
+
language:
|
| 10 |
+
- en
|
| 11 |
+
pipeline_tag: text2text-generation
|
| 12 |
+
widget:
|
| 13 |
+
- text: >-
|
| 14 |
+
how can I become more healthy?
|
| 15 |
+
example_title: example
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 19 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 20 |
+
|
| 21 |
+
<p align="center" width="100%">
|
| 22 |
+
<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>
|
| 23 |
+
</p>
|
| 24 |
+
|
| 25 |
+
# LaMini-Flan-T5-248M
|
| 26 |
+
|
| 27 |
+
[]()
|
| 28 |
+
|
| 29 |
+
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/).
|
| 30 |
+
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.
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
## Use
|
| 34 |
+
|
| 35 |
+
### Intended use
|
| 36 |
+
We recommend using the model to response to human instructions written in natural language.
|
| 37 |
+
|
| 38 |
+
We now show you how to load and use our model using HuggingFace `pipeline()`.
|
| 39 |
+
|
| 40 |
+
```python
|
| 41 |
+
# pip install -q transformers
|
| 42 |
+
from transformers import pipeline
|
| 43 |
+
|
| 44 |
+
checkpoint = "{model_name}"
|
| 45 |
+
|
| 46 |
+
model = pipeline('text2text-generation', model = checkpoint)
|
| 47 |
+
|
| 48 |
+
input_prompt = 'Please let me know your thoughts on the given place and why you think it deserves to be visited: \n"Barcelona, Spain"'
|
| 49 |
+
generated_text = model(input_prompt, max_length=512, do_sample=True)[0]['generated_text']
|
| 50 |
+
|
| 51 |
+
print("Response", generated_text)
|
| 52 |
+
```
|
| 53 |
+
|
| 54 |
+
## Training Procedure
|
| 55 |
+
|
| 56 |
+
<p align="center" width="100%">
|
| 57 |
+
<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>
|
| 58 |
+
</p>
|
| 59 |
+
|
| 60 |
+
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.
|
| 61 |
+
|
| 62 |
+
### Training Hyperparameters
|
| 63 |
+
|
| 64 |
+
The following hyperparameters were used during training:
|
| 65 |
+
- learning_rate: 0.0005
|
| 66 |
+
- train_batch_size: 128
|
| 67 |
+
- eval_batch_size: 64
|
| 68 |
+
- seed: 42
|
| 69 |
+
- gradient_accumulation_steps: 4
|
| 70 |
+
- total_train_batch_size: 512
|
| 71 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 72 |
+
- lr_scheduler_type: linear
|
| 73 |
+
- num_epochs: 5
|
| 74 |
+
|
| 75 |
+
## Evaluation
|
| 76 |
+
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]().
|
| 77 |
+
|
| 78 |
+
## Limitations
|
| 79 |
+
|
| 80 |
+
More information needed
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
# Citation
|
| 84 |
+
|
| 85 |
+
```bibtex
|
| 86 |
+
@article{lamini-lm,
|
| 87 |
+
author = {Minghao Wu and
|
| 88 |
+
Abdul Waheed and
|
| 89 |
+
Chiyu Zhang and
|
| 90 |
+
Muhammad Abdul-Mageed and
|
| 91 |
+
Alham Fikri Aji
|
| 92 |
+
},
|
| 93 |
+
title = {LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions},
|
| 94 |
+
journal = {CoRR},
|
| 95 |
+
volume = {abs/2304.14402},
|
| 96 |
+
year = {2023},
|
| 97 |
+
url = {https://arxiv.org/abs/2304.14402},
|
| 98 |
+
eprinttype = {arXiv},
|
| 99 |
+
eprint = {2304.14402}
|
| 100 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 101 |
```
|