pythia-70m-deduped-aid
Model description
This model is a finetune of EleutherAI/pythia-70m-deduped (from when it was instead pythia-19m-deduped), on the text_adventures.txt dataset originally intended for AI Dungeon 2. Performance will be very poor, as expected by the small model, and generations may be offensive thanks to its training data.
This model was trained for testing purposes and was intended for use with KoboldAI. A temperature of 0.5 and a repetition penalty of 1.01 were tested.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
- Downloads last month
- 12
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.