Instructions to use Davlan/afro-xlmr-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Davlan/afro-xlmr-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="Davlan/afro-xlmr-large")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("Davlan/afro-xlmr-large") model = AutoModelForMaskedLM.from_pretrained("Davlan/afro-xlmr-large", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,44 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: afro-xlmr-base
|
| 7 |
+
results: []
|
| 8 |
---
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
# afro-xlmr-base
|
| 12 |
+
|
| 13 |
+
AfroXLMR-base was created by MLM adaptation of XLM-R-base model on 17 African languages (Afrikaans, Amharic, Hausa, Igbo, Malagasy, Chichewa, Oromo, Naija, Kinyarwanda, Kirundi, Shona, Somali, Sesotho, Swahili, isiXhosa, Yoruba, and isiZulu) covering the major African language families and 3 high resource languages (Arabic, French, and English).
|
| 14 |
+
|
| 15 |
+
## Eval results on MasakhaNER (F-score)
|
| 16 |
+
language| XLM-R-miniLM| XLM-R-base |XLM-R-large | afro-xlmr-base | afro-xlmr-base | afro-xlmr-small | afro-xlmr-mini
|
| 17 |
+
-|-|-|-|-|-|-
|
| 18 |
+
amh |69.5|70.6|76.2|--|76.1|70.1|69.7
|
| 19 |
+
hau |74.5|89.5|90.5|--|91.2|91.4|87.7
|
| 20 |
+
ibo |81.9|84.8|84.1|--|87.4|86.6|83.5
|
| 21 |
+
kin |68.6|73.3|73.8|--|78.0|77.5|74.1
|
| 22 |
+
lug |64.7|79.7|81.6|--|82.9|83.2|77.4
|
| 23 |
+
luo |11.7|74.9|73.6|--|75.1|75.4|17.5
|
| 24 |
+
pcm |83.2|87.3|89.0|--|89.6|89.0|85.5
|
| 25 |
+
swa |86.3|87.4|89.4|--|88.6|88.7|86.0
|
| 26 |
+
wol |51.7|63.9|67.9|--|67.4|65.9|59.0
|
| 27 |
+
yor |72.0|78.3|78.9|85.0|82.1|81.3|75.1
|
| 28 |
+
|
| 29 |
+
### BibTeX entry and citation info
|
| 30 |
+
```
|
| 31 |
+
@misc{afro_maft,
|
| 32 |
+
doi = {10.48550/ARXIV.2204.06487},
|
| 33 |
+
url = {https://arxiv.org/abs/2204.06487},
|
| 34 |
+
author = {Alabi, Jesujoba O. and Adelani, David Ifeoluwa and Mosbach, Marius and Klakow, Dietrich},
|
| 35 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
| 36 |
+
title = {Multilingual Language Model Adaptive Fine-Tuning: A Study on African Languages},
|
| 37 |
+
publisher = {arXiv},
|
| 38 |
+
year = {2022},
|
| 39 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
| 40 |
+
}
|
| 41 |
+
|
| 42 |
+
```
|
| 43 |
+
|
| 44 |
+
|