Sentence Similarity
sentence-transformers
Safetensors
English
French
German
bert
feature-extraction
job-titles
retrieval
contrastive-learning
matryoshka
cross-lingual
esco
onet
text-embeddings-inference
Instructions to use Misbahuddin/job-title-normalizer-e5-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Misbahuddin/job-title-normalizer-e5-small with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Misbahuddin/job-title-normalizer-e5-small") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Point demo link at Cloud Run deployment
Browse files
README.md
CHANGED
|
@@ -29,7 +29,7 @@ canonical occupation taxonomy** (ESCO + O*NET), framed as retrieval over 4,055 c
|
|
| 29 |
occupations. ~2.5× smaller and faster than the e5-base variant at a modest accuracy cost —
|
| 30 |
the right choice for CPU serving and bulk backfills.
|
| 31 |
|
| 32 |
-
**Live demo:**
|
| 33 |
|
| 34 |
## Results
|
| 35 |
|
|
|
|
| 29 |
occupations. ~2.5× smaller and faster than the e5-base variant at a modest accuracy cost —
|
| 30 |
the right choice for CPU serving and bulk backfills.
|
| 31 |
|
| 32 |
+
**Live demo:** <https://job-title-normalizer-525186107937.us-central1.run.app> (Cloud Run; may cold-start ~1 min)
|
| 33 |
|
| 34 |
## Results
|
| 35 |
|