Translation
Transformers
Safetensors
PEFT
Ancient Greek (to 1453)
Greek
machine-translation
ancient-greek
modern-greek
m2m100
qlora
natural language processing
computational linguistics
Instructions to use ilsp/m2m100-1.2B-ag-mg-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ilsp/m2m100-1.2B-ag-mg-qlora 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="ilsp/m2m100-1.2B-ag-mg-qlora")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ilsp/m2m100-1.2B-ag-mg-qlora", device_map="auto") - PEFT
How to use ilsp/m2m100-1.2B-ag-mg-qlora with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -206,16 +206,4 @@ If you use this model, please cite our LREC 2026 paper:
|
|
| 206 |
}
|
| 207 |
```
|
| 208 |
|
| 209 |
-
|
| 210 |
-
|
| 211 |
-
```bibtex
|
| 212 |
-
@mastersthesis{mavromatis2026thesis,
|
| 213 |
-
author = {Spyridon Mavromatis},
|
| 214 |
-
title = {Ancient Greek to Modern Greek Machine Translation: A Novel Benchmark and Fine-Tuning Experiments on LLMs and NMT Models},
|
| 215 |
-
school = {National and Kapodistrian University of Athens and Institute for Language and Speech Processing, "Athena" Research Center},
|
| 216 |
-
year = {2026},
|
| 217 |
-
address = {Athens, Greece},
|
| 218 |
-
url = {https://pergamos.lib.uoa.gr/uoa/dl/object/5320989},
|
| 219 |
-
note = {The fine-tuned models are publicly released; the accompanying AG-MG Parallel Corpus is not publicly distributed due to the complex and uncertain copyright status of the source materials.}
|
| 220 |
-
}
|
| 221 |
-
```
|
|
|
|
| 206 |
}
|
| 207 |
```
|
| 208 |
|
| 209 |
+
**Note on resources:** The fine-tuned models are publicly released. The accompanying AG-MG Parallel Corpus is not publicly distributed due to the complex and uncertain copyright status of the source materials.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|