# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("Anhptp/opus-mt-en-es-BDS-G1")
model = AutoModelForSeq2SeqLM.from_pretrained("Anhptp/opus-mt-en-es-BDS-G1", device_map="auto")Quick Links
opus-mt-en-es-BDS-G1
This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-es on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9611
- Bleu: 51.5683
- Gen Len: 9.365
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.0722 | 1.0 | 625 | 0.9611 | 51.5683 | 9.365 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 6
Model tree for Anhptp/opus-mt-en-es-BDS-G1
Base model
Helsinki-NLP/opus-mt-en-es
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="Anhptp/opus-mt-en-es-BDS-G1")