Downloads · 30 days
31
0% of all-time downloads
quote-generator
nandinib1999/quote-generator
quote-generator is a text generation model from nandinib1999. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as cc.
This is a GPT2 model fine-tuned on the Quotes-500K dataset.
All-time downloads
6.2K
Public
Repo size
1.5 GB
Likes
5
Public
Repo makeup
Click a slice to open those files.
.bin510 MB · 51%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- cc
- Model type
- gpt2
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Mar 6, 2022
- SHA
- 43fed603
Try a prompt
Datasets
Model card
From the Hugging Face model README
Quotes Generator
Model description
This is a GPT2 model fine-tuned on the Quotes-500K dataset.
Intended uses & limitations
For a given user prompt, it can generate motivational quotes starting with it.
How to use
from transformers import AutoTokenizer, AutoModelWithLMHead
tokenizer = AutoTokenizer.from_pretrained("nandinib1999/quote-generator")
model = AutoModelWithLMHead.from_pretrained("nandinib1999/quote-generator")
Training data
This is the distribution of the total dataset into training, validation and test dataset for the fine-tuning task.
<table style="width:30%"> <tr> <th>train</th> <td>349796</td> </tr> <tr> <th>validation</th> <td>99942</td> </tr> <tr> <th>test</th> <td>49971</td> </tr> </table>Training procedure
The model was fine-tuned using the Google Colab GPU for one epoch. The weights of the pre-trained GPT2 model were used as a base.
Eval results
<table style="width:30%"> <tr> <th>Epoch</th> <th>Perplexity</th> </tr> <tr> <td>1</td> <td>15.180</td> </tr> </table>- Task
- Text Generation
- Library
- transformers
- Type
- gpt2
- License
- cc
- Languages
- en
- Created
- Mar 2, 2022
- Updated
- Mar 6, 2022