Instructions to use zenoverflow/madlad400-3b-mt-int8-float32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zenoverflow/madlad400-3b-mt-int8-float32 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="zenoverflow/madlad400-3b-mt-int8-float32")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("zenoverflow/madlad400-3b-mt-int8-float32", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
pipeline_tag: translation
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
Quantization of [madlad400-3b-mt](https://huggingface.co/google/madlad400-3b-mt) using [Ctranslate2](https://github.com/OpenNMT/CTranslate2) for running on CPU.
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
pipeline_tag: translation
|
| 4 |
+
inference: false
|
| 5 |
---
|
| 6 |
|
| 7 |
Quantization of [madlad400-3b-mt](https://huggingface.co/google/madlad400-3b-mt) using [Ctranslate2](https://github.com/OpenNMT/CTranslate2) for running on CPU.
|