- Forward hf_token to FastSentenceTransformer.from_pretrained() so private/gated embedding repos authenticate correctly - Key _embedding_detection_cache by (model_name, hf_token) tuple so unauthenticated lookups don't shadow subsequent authenticated ones |
||
|---|---|---|
| .. | ||
| data_recipe | ||
| export | ||
| inference | ||
| training | ||
| __init__.py | ||