Downloads · 30 days
4
1% of all-time downloads
gpt-sw3-126m-njala
Sigurdur/gpt-sw3-126m-njala
gpt-sw3-126m-njala is a text generation model from Sigurdur. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/
All-time downloads
367
Public
Parameters
136M
544 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors543 MB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- other
- Model type
- gpt2
- Access
- Public
- Created
- Jul 7, 2024
- Updated
- Jul 7, 2024
- SHA
- cc35999d
Base models
Datasets
Model card
From the Hugging Face model README
gpt-sw3-126m-njala
This model is a fine-tuned version of AI-Sweden-Models/gpt-sw3-126m on Sigurdur/njala.
Model description
More information needed
Intended uses & limitations
For writing in the style of the Icelandic sagas, specifically Brennu-Njáls Saga
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1
- Task
- Text Generation
- Library
- transformers
- Type
- gpt2
- License
- other
- Languages
- is
- Created
- Jul 7, 2024
- Updated
- Jul 7, 2024