Downloads · 30 days
7
7% of all-time downloads
v9ai/salescue-entities-v1
salescue-entities-v1 is a token classification model from v9ai. Use it when you need labels on individual words, such as names. It is set up for salescue. The card lists the license as mit.
EntityExtractor module from the SalesCue sales intelligence library.
Downloads · 30 days
7
7% of all-time downloads
All-time downloads
95
Public
Repo size
4.1 MB
Likes
0
Public
Click a slice to open those files.
.pt1 MB · 100%
From the Hugging Face model README
EntityExtractor module from the SalesCue sales intelligence library.
Status:
untrained— architecture only, random initialization. Use as a starting point for fine-tuning.
Regex + Pointer NER with Re-typing
Hybrid entity extraction combining high-precision regex patterns for structured entities (emails, phones, URLs, money, dates) with a pointer-network NER for unstructured entities (person, company, product, role). A re-typing layer reclassifies detected entities in context — e.g., "John" becomes decision_maker vs. reference based on surrounding text.
from salescue import SalesCueModel
model = SalesCueModel.from_pretrained("v9ai/salescue-entities-v1")
result = model.predict("your sales text here")
print(result)
personcompanyproductrolelocationtechnologymicrosoft/deberta-v3-base (shared encoder, 768-dim)EntityExtractormicrosoft/deberta-v3-base loaded via the SalesCue library.SalesCue is a sales intelligence library with 12 ML modules sharing a single DeBERTa-v3-base encoder backbone. Modules can be composed via Unix-style piping:
from salescue import Document
result = Document("interested in pricing") | ai.score | ai.intent | ai.sentiment
All modules: score intent reply triggers icp objection sentiment spam entities call subject emailgen
See the SalesCue documentation for details.