Downloads · 30 days
328
0% of all-time downloads
prompt-extend
daspartho/prompt-extend
prompt-extend is a text generation model from daspartho. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
[](https://huggingface.co/spaces/daspartho/prompt-extend)
All-time downloads
345K
Public
Repo size
20.1 GB
Likes
37
Public
Repo makeup
Click a slice to open those files.
.bin516 MB · 99%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mit
- Model type
- gpt2
- Access
- Public
- Created
- Nov 1, 2022
- Updated
- Dec 20, 2022
- SHA
- d6573fca
Try a prompt
Model card
From the Hugging Face model README
Prompt Extend
Text generation model for generating suitable style cues given the main idea for a prompt.
It is a GPT-2 model trained on dataset of stable diffusion prompts.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 128
- eval_batch_size: 256
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.7436 | 1.0 | 12796 | 2.5429 |
| 2.3292 | 2.0 | 25592 | 2.0711 |
| 1.9439 | 3.0 | 38388 | 1.8447 |
| 1.7059 | 4.0 | 51184 | 1.7325 |
| 1.5775 | 5.0 | 63980 | 1.7110 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1
- Tokenizers 0.13.2
- Task
- Text Generation
- Library
- transformers
- Type
- gpt2
- License
- mit
- Created
- Nov 1, 2022
- Updated
- Dec 20, 2022