kant-gpt2-large

Anjoe/kant-gpt2-large

kant-gpt2-large is a text generation model from Anjoe. 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.

This model is a fine-tuned version of benjamin/gerpt2-large. It was trained on the "Akademie Ausgabe" of the works of Immanuel Kant. It achieves the following results on the evaluation set: - Loss: 3.4257

Downloads · 30 days

3% of all-time downloads

All-time downloads

2.2K

Public

Repo size

21.9 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin3.1 GB · 100%

At a glance

Task: Text Generation
Library: transformers
License: mit
Model type: gpt2
Access: Public
Created: Jun 13, 2022
Updated: Jul 21, 2022
SHA: 2e4fda37

Try a prompt

Model card

From the Hugging Face model README

kant-gpt2-large

This model is a fine-tuned version of benjamin/gerpt2-large. It was trained on the "Akademie Ausgabe" of the works of Immanuel Kant. It achieves the following results on the evaluation set:

Loss: 3.4257

Model description

A large version of gpt2

Intended uses & limitations

It could be used for the analysis of knowledge representation in and extraction from large language models

Training and evaluation data

Akademie Ausgabe Immanuel Kant

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
3.4094	1.0	11308	3.3838
3.0445	2.0	22616	3.3107
2.7161	3.0	33924	3.3409
2.4793	4.0	45232	3.4257

Framework versions

Transformers 4.20.1
Pytorch 1.11.0+cu113
Datasets 2.3.2
Tokenizers 0.12.1

Task: Text Generation
Library: transformers
Type: gpt2
License: mit
Created: Jun 13, 2022
Updated: Jul 21, 2022