Instructions to use projecte-aina/Plume32k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use projecte-aina/Plume32k 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/Plume32k")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("projecte-aina/Plume32k") model = AutoModelForCausalLM.from_pretrained("projecte-aina/Plume32k", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,12 +13,15 @@ language:
|
|
| 13 |
metrics:
|
| 14 |
- comet
|
| 15 |
- bleu
|
| 16 |
-
pipeline_tag:
|
| 17 |
widget:
|
| 18 |
-
|
|
|
|
|
|
|
| 19 |
inference:
|
| 20 |
parameters:
|
| 21 |
-
|
|
|
|
| 22 |
---
|
| 23 |
|
| 24 |
# Plume32k
|
|
|
|
| 13 |
metrics:
|
| 14 |
- comet
|
| 15 |
- bleu
|
| 16 |
+
pipeline_tag: text-generation
|
| 17 |
widget:
|
| 18 |
+
- text: |-
|
| 19 |
+
<s> [spa_Latn] Ayer se fue, tomó sus cosas y se puso a navegar.
|
| 20 |
+
[cat_Latn]
|
| 21 |
inference:
|
| 22 |
parameters:
|
| 23 |
+
max_new_tokens: 120
|
| 24 |
+
return_full_text: False
|
| 25 |
---
|
| 26 |
|
| 27 |
# Plume32k
|