|
|
--- |
|
|
license: mit |
|
|
base_model: gpt2 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: Model_1B_Bush |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# Model_1B_Bush |
|
|
|
|
|
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on a large corpus of George W. Bush's first term discourse on terrorism. |
|
|
|
|
|
## To Prompt the Model |
|
|
|
|
|
Try entering single words or short phrases, such as "terrorism is" or "national security" or "our foreign policy should be", |
|
|
in the dialogue box on the right hand side of this page. Then click on 'compute' and wait for the results. The model will take a few seconds |
|
|
to load on your first prompt. |
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
This model is intended as an experiment on the utility of LLMs for discourse analysis on a specific corpus of political rhetoric. |
|
|
|
|
|
|
|
|
### 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: 5.0 |
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.36.0.dev0 |
|
|
- Pytorch 2.1.0+cu118 |
|
|
- Datasets 2.15.0 |
|
|
- Tokenizers 0.15.0 |
|
|
|
