Translation
Transformers
ONNX
Safetensors
Spanish
Aragonese
pegasus
text2text-generation
ctranslate2
opennmt
Instructions to use TigreGotico/nos-mt-es-arg-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TigreGotico/nos-mt-es-arg-onnx with Transformers:
# 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="TigreGotico/nos-mt-es-arg-onnx")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("TigreGotico/nos-mt-es-arg-onnx") model = AutoModelForSeq2SeqLM.from_pretrained("TigreGotico/nos-mt-es-arg-onnx", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "activation_dropout": 0.0, | |
| "activation_function": "relu", | |
| "architectures": [ | |
| "PegasusForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 2, | |
| "d_model": 512, | |
| "decoder_attention_heads": 16, | |
| "decoder_ffn_dim": 2048, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_layers": 12, | |
| "decoder_start_token_id": 2, | |
| "dropout": 0.0, | |
| "dtype": "float32", | |
| "encoder_attention_heads": 16, | |
| "encoder_ffn_dim": 2048, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 12, | |
| "eos_token_id": 3, | |
| "forced_eos_token_id": null, | |
| "init_std": 0.02, | |
| "is_encoder_decoder": true, | |
| "max_length": null, | |
| "max_position_embeddings": 1024, | |
| "model_type": "pegasus", | |
| "num_beams": null, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 1, | |
| "scale_embedding": true, | |
| "static_position_embeddings": true, | |
| "transformers_version": "4.57.6", | |
| "use_cache": true, | |
| "vocab_size": 29632 | |
| } | |