Translation
PEFT
Safetensors
Yoruba
English
Nigerian Pidgin
lora
yoruba
nigerian-pidgin
african-languages
qlora
Instructions to use Jesujuwon/HY-MT1.5-1.8B-yoruba-pidgin-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Jesujuwon/HY-MT1.5-1.8B-yoruba-pidgin-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("tencent/HY-MT1.5-1.8B") model = PeftModel.from_pretrained(base_model, "Jesujuwon/HY-MT1.5-1.8B-yoruba-pidgin-lora") - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -112,7 +112,7 @@ print(translate("Education is the key to a better future.", "Yoruba"))
|
|
| 112 |
- Training data is small (~4,000 pairs); larger Yoruba corpora would improve scores
|
| 113 |
- Nigerian Pidgin pairs are synthetic and limited in dialectal variety
|
| 114 |
- Model inherits base model constraints (no terminology glossary, 1.8B capacity)
|
| 115 |
-
|
| 116 |
|
| 117 |
## Citation
|
| 118 |
|
|
|
|
| 112 |
- Training data is small (~4,000 pairs); larger Yoruba corpora would improve scores
|
| 113 |
- Nigerian Pidgin pairs are synthetic and limited in dialectal variety
|
| 114 |
- Model inherits base model constraints (no terminology glossary, 1.8B capacity)
|
| 115 |
+
|
| 116 |
|
| 117 |
## Citation
|
| 118 |
|