Update Hub IDs to the Qdrant org

README.md

@@ -21,9 +21,9 @@ table instead of a transformer, making it useful when query latency matters more
 retrieval quality.
 
 It produces normalized 1024-dimensional vectors that search documents encoded by
-[`stella-en-400M-v5-doc-onnx`](https://huggingface.co/DylanCouzon/stella-en-400M-v5-doc-onnx).
+[`stella-en-400M-v5-doc-onnx`](https://huggingface.co/Qdrant/stella-en-400M-v5-doc-onnx).
 The same document index also works with the stronger
-[`constella-nano`](https://huggingface.co/DylanCouzon/constella-nano) query encoder.
+[`constella-nano`](https://huggingface.co/Qdrant/constella-nano) query encoder.
 
 > Research preview: Native FastEmbed support currently requires the Constella preview branch
 > shown below. The published evaluation is limited to the results described in this card.
@@ -37,7 +37,7 @@ The same document index also works with the stronger
 | Languages | English |
 | Maximum input length | 512 tokens |
 | Query prefix | None |
-| Document encoder | `DylanCouzon/stella-en-400M-v5-doc-onnx` |
+| Document encoder | `Qdrant/stella-en-400M-v5-doc-onnx` |
 | Recommended retrieval | Hybrid with BM25 and DBSF at prefetch 100 |
 
 ## The Constella family
@@ -69,8 +69,8 @@ database that supports cosine similarity.
 from fastembed import TextEmbedding
 from qdrant_client import QdrantClient, models
 
-NAME = "DylanCouzon/constella-zero"
-DOC_NAME = "DylanCouzon/stella-en-400M-v5-doc-onnx"
+NAME = "Qdrant/constella-zero"
+DOC_NAME = "Qdrant/stella-en-400M-v5-doc-onnx"
 
 documents = [
     "mRNA vaccines deliver messenger RNA encoding a viral antigen.",
@@ -116,7 +116,7 @@ FastEmbed or ONNX Runtime:
 from huggingface_hub import snapshot_download
 import sys
 
-model_directory = snapshot_download("DylanCouzon/constella-zero")
+model_directory = snapshot_download("Qdrant/constella-zero")
 sys.path.insert(0, model_directory)
 
 from zero_encoder import ZeroQueryEncoder