tasal9/ZamAI_Pashto_Dataset
Viewer • Updated • 57.3k • 20
How to use tasal9/ZamAI-Pashto-Translator-FacebookNLB-ps-en 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="tasal9/ZamAI-Pashto-Translator-FacebookNLB-ps-en") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("tasal9/ZamAI-Pashto-Translator-FacebookNLB-ps-en")
model = AutoModelForSeq2SeqLM.from_pretrained("tasal9/ZamAI-Pashto-Translator-FacebookNLB-ps-en", device_map="auto")Task: translation
Languages: ps, en
Base model: facebook/nllb-200-3.3B
Training dataset(s): tasal9/ZamAI_Pashto_Dataset
This model is part of the ZamAI Pashto language AI collection. It is fine-tuned/adapted for translation in Pashto and related languages.
from transformers import pipeline
translator = pipeline("translation", model="tasal9/ZamAI-Pashto-Translator-FacebookNLB-ps-en")
print(translator("سلام دې وي! تاسو څنګه یاست؟", max_length=128))
The model was trained or fine-tuned on: tasal9/ZamAI_Pashto_Dataset.
| Metric | Value | Description |
|---|---|---|
| bleu | TBD | Add measured value |
| sacrebleu | TBD | Add measured value |
| comet | TBD | Add measured value |
Update this table with your measured results and link to the evaluation script/notebook.
@misc{zamai_pashto,
title = {{ZamAI Pashto Translator FacebookNLB ps en}},
author = {ZamAI / Yaqoob Tasal},
year = {2024},
howpublished = {\url{https://huggingface.co/tasal9/ZamAI-Pashto-Translator-FacebookNLB-ps-en}}
}
This model is released under the "apache-2.0" license.
Base model
facebook/nllb-200-3.3B