Translation
Transformers
PyTorch
English
Hindi
viuai
viutranslate
sarus-500m
nmt
english-to-hindi
hindi-to-english
indic
devanagari
bfloat16
zero-synthetic
Instructions to use ViuAI/ViuTranslate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ViuAI/ViuTranslate 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="ViuAI/ViuTranslate")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ViuAI/ViuTranslate", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload RUN_5090.py with huggingface_hub
Browse files- RUN_5090.py +4 -0
RUN_5090.py
CHANGED
|
@@ -12,6 +12,10 @@ import sys
|
|
| 12 |
import shutil
|
| 13 |
import subprocess
|
| 14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
print("=" * 85)
|
| 16 |
print("🚀 Launching ViuTranslate-500M Training on NVIDIA RTX 5090 (32GB VRAM)")
|
| 17 |
print("=" * 85)
|
|
|
|
| 12 |
import shutil
|
| 13 |
import subprocess
|
| 14 |
|
| 15 |
+
# Prevent Jupyter ipykernel crash from progress bar spam
|
| 16 |
+
os.environ["HF_HUB_DISABLE_PROGRESS_BARS"] = "1"
|
| 17 |
+
os.environ["TOKENIZERS_PARALLELISM"] = "false"
|
| 18 |
+
|
| 19 |
print("=" * 85)
|
| 20 |
print("🚀 Launching ViuTranslate-500M Training on NVIDIA RTX 5090 (32GB VRAM)")
|
| 21 |
print("=" * 85)
|