Instructions to use winstxnhdw/nllb-200-distilled-1.3B-ct2-int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use winstxnhdw/nllb-200-distilled-1.3B-ct2-int8 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="winstxnhdw/nllb-200-distilled-1.3B-ct2-int8")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("winstxnhdw/nllb-200-distilled-1.3B-ct2-int8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
40b483e
1
Parent(s): 2fb1f5d
docs: add README
Browse files
README.md
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: translation
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
# nllb-200-distilled-1.3B-ct2-int8
|
| 6 |
+
|
| 7 |
+
This model is used in [nllb-api](https://github.com/winstxnhdw/nllb-api).
|
| 8 |
+
|
| 9 |
+
## Generation
|
| 10 |
+
|
| 11 |
+
The model was generated with the following command.
|
| 12 |
+
|
| 13 |
+
```bash
|
| 14 |
+
ct2-transformers-converter --model facebook/nllb-200-distilled-1.3B --quantization int8 --output_dir converted/nllb-200-distilled-1.3B-ct2-int8
|
| 15 |
+
```
|