Downloads · 30 days
5
10% of all-time downloads
startup-email-lead-classifier
RyzenShivansh/startup-email-lead-classifier
startup-email-lead-classifier is a text classification model from RyzenShivansh. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
distilbert/distilroberta-base fine-tuned to classify purchase-oriented service inquiries (serviceinquiry) versus other incoming email (notserviceinquiry). Production serving uses the included ONNX INT8 model and valid…
All-time downloads
52
Public
Parameters
82.1M
578 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors328 MB · 79%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- roberta
- Access
- Public
- Created
- Aug 5, 2026
- Updated
- Aug 5, 2026
- SHA
- 56e33cfd
Try a prompt
Model card
From the Hugging Face model README
Startup service-inquiry email classifier
distilbert/distilroberta-base fine-tuned to classify purchase-oriented service inquiries (service_inquiry) versus
other incoming email (not_service_inquiry). Production serving uses the included ONNX INT8
model and validation-selected routing thresholds.
Evaluation
Held-out grouped test metrics at threshold 0.1419:
| precision | recall | F1 | average precision |
|---|---|---|---|
| 1.0000 | 0.9825 | 0.9912 | 1.0000 |
These scores only describe the dataset recorded in evaluation/. Synthetic/template examples
are useful for bootstrapping, but do not establish accuracy on a new company's live inbox.
Intended use and limits
- English business email triage; max token length: 384.
- Human review is required for the uncertainty band and high-impact decisions.
- Re-evaluate on a frozen, manually labeled sample of the target inbox before production.
- Do not use this model for employment, credit, medical, or other consequential decisions.
- Email text can contain sensitive data; the API does not log request bodies.
Training provenance
- Base model:
distilbert/distilroberta-base(MIT licensed) - Seed:
42 - Dataset rows after cleaning: 1371
- Labels:
0=not_service_inquiry,1=service_inquiry
Final ONNX INT8 grouped-test results
| precision | recall | F1 | average precision | automatic-lead precision | auto-rejected lead rate |
|---|---|---|---|---|---|
| 1.0000 | 0.9649 | 0.9821 | 1.0000 | 1.0000 | 0.0000 |
INT8 size: 78.763 MB (74.86% smaller than FP32 ONNX).
<!-- INT8_RESULTS_END -->- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- License
- mit
- Languages
- en
- Created
- Aug 5, 2026
- Updated
- Aug 5, 2026