# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("nmthien/vietnamese-gpt2")
model = AutoModelForCausalLM.from_pretrained("nmthien/vietnamese-gpt2", device_map="auto")Quick Links
vietnamese-gpt2
This model is a fine-tuned version of nmthien/vietnamese-gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.1731
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: 0.0002
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.3452 | 0.5 | 500 | 3.1901 |
| 3.3344 | 1.0 | 1000 | 3.1731 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2
- Downloads last month
- 1,003
Model tree for nmthien/vietnamese-gpt2
Unable to build the model tree, the base model loops to the model itself. Learn more.
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nmthien/vietnamese-gpt2")