|
--- |
|
language: en |
|
thumbnail: https://www.huggingtweets.com/gimoyin/1614111899984/predictions.png |
|
tags: |
|
- huggingtweets |
|
widget: |
|
- text: "My dream is" |
|
--- |
|
|
|
<div> |
|
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1241598015405621251/RfMwNmc__400x400.jpg')"> |
|
</div> |
|
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Lake Yin 🤖 AI Bot </div> |
|
<div style="font-size: 15px">@gimoyin bot</div> |
|
</div> |
|
|
|
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets). |
|
|
|
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)! |
|
|
|
## How does it work? |
|
|
|
The model uses the following pipeline. |
|
|
|
 |
|
|
|
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI). |
|
|
|
## Training data |
|
|
|
The model was trained on [@gimoyin's tweets](https://twitter.com/gimoyin). |
|
|
|
| Data | Quantity | |
|
| --- | --- | |
|
| Tweets downloaded | 961 | |
|
| Retweets | 636 | |
|
| Short tweets | 31 | |
|
| Tweets kept | 294 | |
|
|
|
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1leyvbxk/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline. |
|
|
|
## Training procedure |
|
|
|
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @gimoyin's tweets. |
|
|
|
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/y78zi5ra) for full transparency and reproducibility. |
|
|
|
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/y78zi5ra/artifacts) is logged and versioned. |
|
|
|
## How to use |
|
|
|
You can use this model directly with a pipeline for text generation: |
|
|
|
```python |
|
from transformers import pipeline |
|
generator = pipeline('text-generation', |
|
model='huggingtweets/gimoyin') |
|
generator("My dream is", num_return_sequences=5) |
|
``` |
|
|
|
## Limitations and bias |
|
|
|
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias). |
|
|
|
In addition, the data present in the user's tweets further affects the text generated by the model. |
|
|
|
## About |
|
|
|
*Built by Boris Dayma* |
|
|
|
[](https://twitter.com/intent/follow?screen_name=borisdayma) |
|
|
|
For more details, visit the project repository. |
|
|
|
[](https://github.com/borisdayma/huggingtweets) |
|
|
