Instructions to use WindyTranslate/translate-fi-lua with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WindyTranslate/translate-fi-lua 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="WindyTranslate/translate-fi-lua")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("WindyTranslate/translate-fi-lua") model = AutoModelForSeq2SeqLM.from_pretrained("WindyTranslate/translate-fi-lua", device_map="auto") - Notebooks
- Google Colab
- Kaggle
cards: rename merge method lora-fog -> windy-hallmark
Browse files
README.md
CHANGED
|
@@ -24,7 +24,7 @@ licence requires.
|
|
| 24 |
|
| 25 |
| | |
|
| 26 |
|---|---|
|
| 27 |
-
| Method | `
|
| 28 |
| Tensors modified | **36 of 254** |
|
| 29 |
| Max absolute weight delta | **7.628e-05** |
|
| 30 |
| Verified | tensor-by-tensor against the upstream original, 2026-07-26 |
|
|
|
|
| 24 |
|
| 25 |
| | |
|
| 26 |
|---|---|
|
| 27 |
+
| Method | `windy-hallmark` |
|
| 28 |
| Tensors modified | **36 of 254** |
|
| 29 |
| Max absolute weight delta | **7.628e-05** |
|
| 30 |
| Verified | tensor-by-tensor against the upstream original, 2026-07-26 |
|