|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
- opt |
|
model-index: |
|
- name: gptQuotes |
|
results: [] |
|
datasets: |
|
- Abirate/english_quotes |
|
language: |
|
- en |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# gptQuotes |
|
|
|
This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co./facebook/opt-350m) on an Abirate's English Quotes dataset. |
|
|
|
|
|
## Intended uses & limitations |
|
|
|
Generating quotes with AI |
|
|
|
## Online demo |
|
|
|
A demo of this AI is availible in a [Huggingface Space](https://huggingface.co./spaces/sr5434/QuoteGeneration). Do not use the version attached to this model, as it doesn't work. |
|
|
|
## Sample code |
|
``` |
|
from transformers import pipeline |
|
ai = pipeline('text-generation',model='sr5434/gptQuotes', tokenizer='facebook/opt-350m', device=-1)#,config={'max_length':45}) |
|
while True: |
|
result = ai(input("Prompt>>>"))[0]['generated_text'] |
|
print(result) |
|
``` |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- 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: 15 |
|
### Framework versions |
|
- Transformers 4.25.1 |
|
- Pytorch 1.13.1+cu116 |
|
- Tokenizers 0.13.2 |
