File size: 284 Bytes
43035cf |
1 2 3 4 5 6 7 8 9 10 11 12 |
# inference.py
from text_embeddings_runner import EmbeddingRunner
def create_runner():
# Force PyTorch runner on GPU
return EmbeddingRunner.from_pretrained(
repo_id="magnifi/optimized-semcache-embeds-en-final",
backend="pytorch",
device="cuda"
)
|