|
--- |
|
language: |
|
- en |
|
license: mit |
|
library_name: transformers |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- 0Tick/Danbooru-Random-Posts-Scrape |
|
metrics: |
|
- accuracy |
|
co2_eq_emissions: 100 |
|
pipeline_tag: text-generation |
|
base_model: distilgpt2 |
|
model-index: |
|
- name: danbooruTagAutocomplete |
|
results: [] |
|
--- |
|
|
|
## Model description |
|
|
|
This is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) which is intended to be used with the [promptgen](https://github.com/AUTOMATIC1111/stable-diffusion-webui-promptgen) extension inside the AUTOMATIC1111 WebUI. |
|
It is trained on the raw tags of danbooru with underscores and spaces. Only posts with a rating higher than "General" were included in the dataset. |
|
|
|
|
|
# Training |
|
|
|
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on a dataset of the tags of 118k random posts of [danbooru](danbooru.donmai.us) . |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.6934 |
|
- Accuracy: 0.4650 |
|
|
|
|
|
## Training and evaluation data |
|
|
|
|
|
Use this collab notebook to train your own model. Also used to train this model |
|
[](https://colab.research.google.com/github/0Tick/stable-diffusion-tools/blob/main/distilgpt2train.ipynb) |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-05 |
|
- train_batch_size: 6 |
|
- eval_batch_size: 6 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3.0 |
|
|
|
## Intended uses & limitations |
|
|
|
Since DistilGPT2 is a distilled version of GPT-2, it is intended to be used for similar use cases with the increased functionality of being smaller and easier to run than the base model. |
|
|
|
The developers of GPT-2 state in their [model card](https://github.com/openai/gpt-2/blob/master/model_card.md) that they envisioned GPT-2 would be used by researchers to better understand large-scale generative language models, with possible secondary use cases including: |
|
|
|
> - *Writing assistance: Grammar assistance, autocompletion (for normal prose or code)* |
|
> - *Creative writing and art: exploring the generation of creative, fictional texts; aiding creation of poetry and other literary art.* |
|
> - *Entertainment: Creation of games, chat bots, and amusing generations.* |
|
|
|
Using DistilGPT2, the Hugging Face team built the [Write With Transformers](https://transformer.huggingface.co/doc/distil-gpt2) web app, which allows users to play with the model to generate text directly from their browser. |
|
|
|
#### Out-of-scope Uses |
|
|
|
OpenAI states in the GPT-2 [model card](https://github.com/openai/gpt-2/blob/master/model_card.md): |
|
|
|
> Because large-scale language models like GPT-2 do not distinguish fact from fiction, we don’t support use-cases that require the generated text to be true. |
|
> |
|
> Additionally, language models like GPT-2 reflect the biases inherent to the systems they were trained on, so we do not recommend that they be deployed into systems that interact with humans unless the deployers first carry out a study of biases relevant to the intended use-case. |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.0.dev0 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.13.2 |
