|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- generated_from_keras_callback |
|
|
model-index: |
|
|
- name: articleGeneratorV1.0 |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information Keras had access to. You should |
|
|
probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# What does model do and how to use it |
|
|
|
|
|
Just provide an title to the model and it will generate a whole article about it. |
|
|
|
|
|
```python |
|
|
# Install transformers library |
|
|
!pip install transformers |
|
|
``` |
|
|
|
|
|
```python |
|
|
# Load tokenizer and model |
|
|
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, TFAutoModelForSeq2SeqLM |
|
|
model_name = "Seungjun/articleGeneratorV1.0" |
|
|
tokenizer = AutoTokenizer.from_pretrained("t5-small") |
|
|
model = TFAutoModelForSeq2SeqLM.from_pretrained(model_name) |
|
|
``` |
|
|
|
|
|
```python |
|
|
# Get the article for a given title |
|
|
from transformers import pipeline |
|
|
summarizer = pipeline("summarization", model=model, tokenizer=tokenizer, framework="tf") |
|
|
summarizer( |
|
|
"Steve Jobs", # title |
|
|
min_length=500, |
|
|
max_length=1024, |
|
|
) |
|
|
``` |
|
|
|
|
|
Result: |
|
|
|
|
|
|
|
|
|
|
|
# Current limitation of the model |
|
|
|
|
|
It generate aot of lies. 99% of the word generated by this model is not true. |
|
|
|
|
|
# articleGeneratorV1.0 |
|
|
|
|
|
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Train Loss: 3.9568 |
|
|
- Validation Loss: 3.6096 |
|
|
- Train Rougel: tf.Tensor(0.08172019, shape=(), dtype=float32) |
|
|
- Epoch: 4 |
|
|
|
|
|
## Model description |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training and evaluation data |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training procedure |
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 2e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False} |
|
|
- training_precision: float32 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Train Loss | Validation Loss | Train Rougel | Epoch | |
|
|
|:----------:|:---------------:|:-----------------------------------------------:|:-----:| |
|
|
| 4.9218 | 4.0315 | tf.Tensor(0.08038119, shape=(), dtype=float32) | 0 | |
|
|
| 4.2887 | 3.8366 | tf.Tensor(0.08103053, shape=(), dtype=float32) | 1 | |
|
|
| 4.1269 | 3.7328 | tf.Tensor(0.081041485, shape=(), dtype=float32) | 2 | |
|
|
| 4.0276 | 3.6614 | tf.Tensor(0.081364945, shape=(), dtype=float32) | 3 | |
|
|
| 3.9568 | 3.6096 | tf.Tensor(0.08172019, shape=(), dtype=float32) | 4 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.27.4 |
|
|
- TensorFlow 2.12.0 |
|
|
- Datasets 2.11.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
