Downloads · 30 days
0
tasal9/ZamAI-Facebook-XLM-Pashto
ZamAI-Facebook-XLM-Pashto is a fill-mask model from tasal9. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as mit.
Task: fill-mask Languages: ps Base model(s): FacebookAI/xlm-roberta-base Training dataset(s): tasal9/ZamAI-Pashto-Dataset-Cleaned
Downloads · 30 days
0
Access
Public
Updated Jul 14, 2026
Repo size
6.3 GB
Likes
0
Public
Click a slice to open those files.
.onnx1.9 GB · 30%
From the Hugging Face model README
Task: fill-mask
Languages: ps
Base model(s): FacebookAI/xlm-roberta-base
Training dataset(s): tasal9/ZamAI-Pashto-Dataset-Cleaned
This model is part of the ZamAI Pashto language AI collection. It is fine-tuned/adapted for fill-mask in Pashto and related languages.
from transformers import pipeline
pipe = pipeline("fill-mask", model="tasal9/ZamAI-Facebook-XLM-Pashto")
print(pipe("کابل د <mask> پلازمینه ده."))
The model was trained or fine-tuned on: tasal9/ZamAI-Pashto-Dataset-Cleaned.
| Metric | Value | Description |
|---|---|---|
| perplexity | TBD | Add measured value |
| accuracy | TBD | Add measured value |
Update this table with your measured results and link to the evaluation script/notebook.
@misc{zamai_pashto,
title = {{ZamAI Facebook XLM Pashto}},
author = {ZamAI / Yaqoob Tasal},
year = {2024},
howpublished = {\url{https://huggingface.co/tasal9/ZamAI-Facebook-XLM-Pashto}}
}
This model is released under the mit license.