Instructions to use WindyTranslate/translate-af-ru with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WindyTranslate/translate-af-ru 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="WindyTranslate/translate-af-ru")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("WindyTranslate/translate-af-ru", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add tokenizer files to the herm0-ct2-int8 folder so it is usable standalone
Browse filesThe folder shipped config.json + model.bin + shared_vocabulary.json only. CTranslate2 loads those, but translating needs the Marian tokenizer, which lived one folder away in herm0/ - so a developer downloading just this variant got a model they could not run. Files copied from herm0/ in this same repo and verified by an end-to-end translation before upload. Weights untouched. Dr. J (Opus 5), clinic log doctor-logs/2026-08-05_stt-fleet-qa.md
- .gitattributes +1 -0
- herm0-ct2-int8/target.spm +3 -0
.gitattributes
CHANGED
|
@@ -38,3 +38,4 @@ lora/target.spm filter=lfs diff=lfs merge=lfs -text
|
|
| 38 |
herm0/source.spm filter=lfs diff=lfs merge=lfs -text
|
| 39 |
herm0/target.spm filter=lfs diff=lfs merge=lfs -text
|
| 40 |
herm0-ct2-int8/source.spm filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 38 |
herm0/source.spm filter=lfs diff=lfs merge=lfs -text
|
| 39 |
herm0/target.spm filter=lfs diff=lfs merge=lfs -text
|
| 40 |
herm0-ct2-int8/source.spm filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
herm0-ct2-int8/target.spm filter=lfs diff=lfs merge=lfs -text
|
herm0-ct2-int8/target.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86feeee4fa9eb2bd69a0e01d8d208de13df8796b9b53cbd98e0af9d33594a3bd
|
| 3 |
+
size 1065693
|