Instructions to use Helsinki-NLP/opus-tatoeba-it-he with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-tatoeba-it-he 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="Helsinki-NLP/opus-tatoeba-it-he")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-tatoeba-it-he") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-tatoeba-it-he", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Fix weights by putting the right value in `lm_head.weight`
#2
by sgugger - opened
- pytorch_model.bin +2 -2
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36807f12793eff840995bd681fa46778658faa02bbb5ff8c65477f789bd1ff7c
|
| 3 |
+
size 153133317
|