upstream-archive/fastembed
1
0
Fork 0
mirror of https://github.com/qdrant/fastembed.git synced 2026-07-23 11:20:51 -05:00
Code Issues Packages Projects Releases Wiki Activity

Add support for jinaai/jina-embeddings-v2-base-de (#270)

Browse Source 
* feat: add support for SOTA german embedding model with long context length jinaai/jina-embeddings-v2-base-de

* Fix jina de model weight

---------

Co-authored-by: George <panchuk.george@outlook.com>
This commit is contained in:
Klaus Hueck
2024-06-14 13:39:13 +02:00
committed by GitHub
parent 5461012ab1
commit fd0b26f009
2 changed files with 9 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
fastembed/text/jina_onnx_embedding.py
View File

@@ -24,6 +24,14 @@ supported_jina_models = [
"sources": {"hf": "xenova/jina-embeddings-v2-small-en"},
"model_file": "onnx/model.onnx",
},
{
"model": "jinaai/jina-embeddings-v2-base-de",
"dim": 768,
"description": "German embedding model supporting 8192 sequence length",
"size_in_GB": 0.32,
"sources": {"hf": "jinaai/jina-embeddings-v2-base-de"},
"model_file": "onnx/model_fp16.onnx",
},
]

1
tests/test_text_onnx_embeddings.py
View File

@@ -36,6 +36,7 @@ CANONICAL_VECTOR_VALUES = {
),
"jinaai/jina-embeddings-v2-small-en": np.array([-0.0455, -0.0428, -0.0122, 0.0613, 0.0015]),
"jinaai/jina-embeddings-v2-base-en": np.array([-0.0332, -0.0509, 0.0287, -0.0043, -0.0077]),
"jinaai/jina-embeddings-v2-base-de": np.array([-0.0085, 0.0417, 0.0342, 0.0309, -0.0149]),
"nomic-ai/nomic-embed-text-v1": np.array([0.0061, 0.0103, -0.0296, -0.0242, -0.0170]),
"nomic-ai/nomic-embed-text-v1.5": np.array(
[-1.6531514e-02, 8.5380634e-05, -1.8171231e-01, -3.9333291e-03, 1.2763254e-02]