Translation
Transformers
PyTorch
TensorBoard
marian
text2text-generation
Generated from Trainer
Eval Results (legacy)
Instructions to use shed-e/Translation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shed-e/Translation 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="shed-e/Translation")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("shed-e/Translation") model = AutoModelForSeq2SeqLM.from_pretrained("shed-e/Translation") - Notebooks
- Google Colab
- Kaggle
Librarian Bot: Add base_model information to model
#1
by librarian-bot - opened
README.md
CHANGED
|
@@ -7,12 +7,13 @@ datasets:
|
|
| 7 |
- kde4
|
| 8 |
metrics:
|
| 9 |
- bleu
|
|
|
|
| 10 |
model-index:
|
| 11 |
- name: marian-finetuned-kde4-en-to-fr
|
| 12 |
results:
|
| 13 |
- task:
|
| 14 |
-
name: Sequence-to-sequence Language Modeling
|
| 15 |
type: text2text-generation
|
|
|
|
| 16 |
dataset:
|
| 17 |
name: kde4
|
| 18 |
type: kde4
|
|
@@ -20,9 +21,9 @@ model-index:
|
|
| 20 |
split: train
|
| 21 |
args: en-fr
|
| 22 |
metrics:
|
| 23 |
-
-
|
| 24 |
-
type: bleu
|
| 25 |
value: 52.83113187001415
|
|
|
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 7 |
- kde4
|
| 8 |
metrics:
|
| 9 |
- bleu
|
| 10 |
+
base_model: Helsinki-NLP/opus-mt-en-fr
|
| 11 |
model-index:
|
| 12 |
- name: marian-finetuned-kde4-en-to-fr
|
| 13 |
results:
|
| 14 |
- task:
|
|
|
|
| 15 |
type: text2text-generation
|
| 16 |
+
name: Sequence-to-sequence Language Modeling
|
| 17 |
dataset:
|
| 18 |
name: kde4
|
| 19 |
type: kde4
|
|
|
|
| 21 |
split: train
|
| 22 |
args: en-fr
|
| 23 |
metrics:
|
| 24 |
+
- type: bleu
|
|
|
|
| 25 |
value: 52.83113187001415
|
| 26 |
+
name: Bleu
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|