Instructions to use TechWolf/ConTeXT-Skill-Extraction-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use TechWolf/ConTeXT-Skill-Extraction-base with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("TechWolf/ConTeXT-Skill-Extraction-base") 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] - Inference
- Notebooks
- Google Colab
- Kaggle
No SmartTokenPooling implementation file (ModuleNotFoundError: No module named 'sbert_patch') ?
Hi! I'm trying to test out this model, but get
'ModuleNotFoundError: No module named 'sbert_patch''
when trying to init the model model = SentenceTransformer("jensjorisdecorte/ConTeXT-Skill-Extraction-base"). From what I understand by looking at the model repo and the exception, there should be a 'sbert_patch.SmartTokenPooling.SmartTokenPooling' layer implementation file?
Using:
sentence-transformers = "3.1.0"
transformers = "4.44.2"
Also tried with:
sentence-transformers = "^3.3.1"
transformers = "^4.48.0"
If it's not the case of intending to not release this yet, could you please help me out? I want to try out this model for work on a potential research paper ( your work has been of huge help already :) ).
Thanks a lot!