Translation
Transformers
PyTorch
Safetensors
English
German
fsmt
text2text-generation
wmt19
facebook
Instructions to use facebook/wmt19-en-de with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/wmt19-en-de 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="facebook/wmt19-en-de")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("facebook/wmt19-en-de") model = AutoModelForSeq2SeqLM.from_pretrained("facebook/wmt19-en-de") - Inference
- Notebooks
- Google Colab
- Kaggle
Add evaluation results on the de-en config and validation split of wmt19
#2
by autoevaluator HF Staff - opened
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
language:
|
| 3 |
- en
|
| 4 |
- de
|
| 5 |
tags:
|
|
@@ -12,6 +12,30 @@ datasets:
|
|
| 12 |
metrics:
|
| 13 |
- bleu
|
| 14 |
thumbnail: https://huggingface.co/front/thumbnails/facebook.png
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
---
|
| 16 |
|
| 17 |
# FSMT
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
- en
|
| 4 |
- de
|
| 5 |
tags:
|
|
|
|
| 12 |
metrics:
|
| 13 |
- bleu
|
| 14 |
thumbnail: https://huggingface.co/front/thumbnails/facebook.png
|
| 15 |
+
model-index:
|
| 16 |
+
- name: facebook/wmt19-en-de
|
| 17 |
+
results:
|
| 18 |
+
- task:
|
| 19 |
+
type: translation
|
| 20 |
+
name: Translation
|
| 21 |
+
dataset:
|
| 22 |
+
name: wmt19
|
| 23 |
+
type: wmt19
|
| 24 |
+
config: de-en
|
| 25 |
+
split: validation
|
| 26 |
+
metrics:
|
| 27 |
+
- name: BLEU
|
| 28 |
+
type: bleu
|
| 29 |
+
value: 47.3619
|
| 30 |
+
verified: true
|
| 31 |
+
- name: loss
|
| 32 |
+
type: loss
|
| 33 |
+
value: 7.284519672393799
|
| 34 |
+
verified: true
|
| 35 |
+
- name: gen_len
|
| 36 |
+
type: gen_len
|
| 37 |
+
value: 29.2205
|
| 38 |
+
verified: true
|
| 39 |
---
|
| 40 |
|
| 41 |
# FSMT
|