Instructions to use projecte-aina/Plume256k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use projecte-aina/Plume256k 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="projecte-aina/Plume256k")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("projecte-aina/Plume256k") model = AutoModelForCausalLM.from_pretrained("projecte-aina/Plume256k") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -107,9 +107,9 @@ Below are the evaluation results on Flores-200 and NTREX for supervised MT direc
|
|
| 107 |
| NLLB-1.3B | 31.02 | 0.86 | 29.68 | 0.85 |
|
| 108 |
| NLLB-600M | 29.24 | 0.85 | 28.37 | 0.84 |
|
| 109 |
| Bilinguals BSC | 31.93 | 0.86 | 29.77 | 0.84 |
|
| 110 |
-
| **
|
| 111 |
-
| **
|
| 112 |
-
| **
|
| 113 |
|
| 114 |
|
| 115 |
## Citation
|
|
|
|
| 107 |
| NLLB-1.3B | 31.02 | 0.86 | 29.68 | 0.85 |
|
| 108 |
| NLLB-600M | 29.24 | 0.85 | 28.37 | 0.84 |
|
| 109 |
| Bilinguals BSC | 31.93 | 0.86 | 29.77 | 0.84 |
|
| 110 |
+
| **Plume 32k** | 30.44 | 0.86 | 28.46 | 0.84 |
|
| 111 |
+
| **Plume 128k** | 30.81 | 0.86 | 28.78 | 0.84 |
|
| 112 |
+
| **Plume 256k** | 30.72 | 0.86 | 28.87 | 0.84 |
|
| 113 |
|
| 114 |
|
| 115 |
## Citation
|