tasal9/ZamAI_Pashto_Dataset
Viewer • Updated • 57.3k • 26
How to use tasal9/ZamAI-QA-Pashto with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("question-answering", model="tasal9/ZamAI-QA-Pashto") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("tasal9/ZamAI-QA-Pashto")
model = AutoModelForCausalLM.from_pretrained("tasal9/ZamAI-QA-Pashto", device_map="auto")Task: question-answering
Languages: ps, en
Training dataset(s): tasal9/ZamAI_Pashto_Dataset
This model is part of the ZamAI Pashto language AI collection. It is fine-tuned/adapted for question-answering in Pashto and related languages.
from transformers import pipeline
qa = pipeline("question-answering", model="tasal9/ZamAI-QA-Pashto")
context = "کابل د افغانستان پلازمینه ده."
question = "د افغانستان پلازمینه څه ده؟"
print(qa(question=question, context=context))
The model was trained or fine-tuned on: tasal9/ZamAI_Pashto_Dataset.
| Metric | Value | Description |
|---|---|---|
| exact_match | TBD | Add measured value |
| f1 | TBD | Add measured value |
Update this table with your measured results and link to the evaluation script/notebook.
@misc{zamai_pashto,
title = {{ZamAI QA Pashto}},
author = {ZamAI / Yaqoob Tasal},
year = {2024},
howpublished = {\url{https://huggingface.co/tasal9/ZamAI-QA-Pashto}}
}
This model is released under the "apache-2.0" license.