Instructions to use AnTechAI/vit5-vietnamese-summarization-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AnTechAI/vit5-vietnamese-summarization-base with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("AnTechAI/vit5-vietnamese-summarization-base") model = AutoModelForSeq2SeqLM.from_pretrained("AnTechAI/vit5-vietnamese-summarization-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from AnTechAI/vit5-vietnamese-summarization-base: direct link, hf CLI and curl.
- Browser
- Download file 1.99 kB
-
https://huggingface.co/AnTechAI/vit5-vietnamese-summarization-base/resolve/main/README.md
- Command line
-
hf download hf://AnTechAI/vit5-vietnamese-summarization-base/README.md
-
curl -L -o README.md https://huggingface.co/AnTechAI/vit5-vietnamese-summarization-base/resolve/main/README.md
1.99 kB
metadata
library_name: transformers
license: mit
base_model: VietAI/vit5-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: vit5-vietnamese-summarization-base
results: []
vit5-vietnamese-summarization-base
This model is a fine-tuned version of VietAI/vit5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7415
- Rouge1: 0.7545
- Rouge2: 0.4629
- Rougel: 0.4807
- Rougelsum: 0.4809
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:
- learning_rate: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 0.8025 | 1.0 | 675 | 0.8079 | 0.7224 | 0.4145 | 0.445 | 0.445 |
| 0.7254 | 2.0 | 1350 | 0.7613 | 0.7466 | 0.4464 | 0.4696 | 0.4697 |
| 0.6798 | 3.0 | 2025 | 0.7451 | 0.7527 | 0.4583 | 0.4788 | 0.479 |
| 0.6402 | 4.0 | 2700 | 0.7415 | 0.7545 | 0.4629 | 0.4807 | 0.4809 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.6.0+cu124
- Datasets 4.4.1
- Tokenizers 0.22.1