Zero-Shot Classification
Transformers
qwen3_5
feature-extraction
decision-model
system-one
semantic-router
vela
token-classification
named-entity-recognition
relation-extraction
pii-detection
hallucination-detection
content-safety
multimodal
custom_code
Eval Results
Instructions to use vllm-sr/vela3-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vllm-sr/vela3-mini with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="vllm-sr/vela3-mini", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("vllm-sr/vela3-mini", trust_remote_code=True) model = AutoModel.from_pretrained("vllm-sr/vela3-mini", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Improving Multilingual Support and NER Accuracy
#3
by BuiDoan - opened
Vela 3 is moving in the right direction by extending decision models with entity and relation extraction.
In my initial tests, PII extraction performed reasonably well, but general NER was noticeably less reliable.
I hope future releases focus on improving NER accuracy and strengthening multilingual NER/PII extraction.