Sentence Similarity
sentence-transformers
ONNX
Safetensors
Transformers.js
modernbert
feature-extraction
embeddings
retrieval
bge-m3
distillation
mmbert
text-embeddings-inference
Instructions to use Horizon-Labs/multilingual-embedding-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Horizon-Labs/multilingual-embedding-base with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Horizon-Labs/multilingual-embedding-base") sentences = [ "How tall is the Eiffel Tower?", "La tour Eiffel mesure 330 mètres.", "Der Eiffelturm ist das höchste Bauwerk von Paris.", "The Statue of Liberty is 93 metres tall.", "Ich esse gern Pizza." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [5, 5] - Transformers.js
How to use Horizon-Labs/multilingual-embedding-base with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('feature-extraction', 'Horizon-Labs/multilingual-embedding-base'); - Notebooks
- Google Colab
- Kaggle
Add SHA256SUMS for the model files
Browse files- SHA256SUMS +14 -0
SHA256SUMS
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
1a662e9248846ab16e0c5caf2363e1ab7a713f102f1d030f3adc044d58782cd6 1_Pooling/config.json
|
| 2 |
+
c624d67a37b76555c0a24e7706428c59dcd8974e2850ae010245429702f14cf7 2_Dense/config.json
|
| 3 |
+
54079ba3cc4f5a530208442dc5edc992959a0302bfc029d823cb2ecbc400fbc1 2_Dense/model.safetensors
|
| 4 |
+
0cf300f2c1b3e3edb4cb2898b3a95520c4feb7c43d6f5440720e72826be5ffaa config.json
|
| 5 |
+
49298c66fe8591c18fdbcdaa3c89e77982f61862e2c37068118c63af57ec2538 config_sentence_transformers.json
|
| 6 |
+
4492406536ba29beaaa21b891a13442a4ca81d3c7c96338ab9fec6aa599b5aaa model.safetensors
|
| 7 |
+
54dc8d2429b26d8e1d3c42098d97dd8b03a425e9e2dd9cdc54ea2f05a272fecc modules.json
|
| 8 |
+
4faca1585b2bb2ceb5443aa13e4ed543f9148a7f81bd4808cd4bb813cd0d82f7 onnx/model.onnx
|
| 9 |
+
7aace31160d136c30afca8e42de7dd398a8e62ab192063c735bb16886bb71b7d onnx/model_quantized.onnx
|
| 10 |
+
1db073805d42ca0f4f4070af3880873f43b2916d0ab2b9e78ee8092f6a298ab5 onnx/quantization_check.json
|
| 11 |
+
8bbfc33e44f66023c526ba86cfc4782918a5885562275996e94a573331be3ba0 sentence_bert_config.json
|
| 12 |
+
baec30ea10906f16adb8c18af7a34023002c1746542612b8b41c9f09e1351351 special_tokens_map.json
|
| 13 |
+
0a5069feab370ece9f452dcda41c0ba2c216eebf6cb49b06893698f53cdc2b0b tokenizer.json
|
| 14 |
+
1d2f82c1341a79748e00efe82e67690f99d00b3c2a894f2b23128fd9d3519da3 tokenizer_config.json
|