Instructions to use Pretam/NIOS_Trilingual_Decoder_Biased with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Pretam/NIOS_Trilingual_Decoder_Biased with PEFT:
from peft import PeftModel from transformers import AutoModelForSeq2SeqLM base_model = AutoModelForSeq2SeqLM.from_pretrained("facebook/nllb-200-distilled-600M") model = PeftModel.from_pretrained(base_model, "Pretam/NIOS_Trilingual_Decoder_Biased") - Transformers
How to use Pretam/NIOS_Trilingual_Decoder_Biased with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Pretam/NIOS_Trilingual_Decoder_Biased", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 10.0, | |
| "eval_avg_bleu": 20.0189, | |
| "eval_gen_len": 27.1703, | |
| "eval_loss": 3.1360061168670654, | |
| "eval_runtime": 3043.4197, | |
| "eval_samples": 10370, | |
| "eval_samples_per_second": 3.407, | |
| "eval_steps_per_second": 0.426, | |
| "total_flos": 1.2426966463650202e+17, | |
| "train_loss": 5.026907345643823, | |
| "train_runtime": 19932.1348, | |
| "train_samples": 98002, | |
| "train_samples_per_second": 49.168, | |
| "train_steps_per_second": 1.537 | |
| } |