Running
4
Safety Copilot
📚
Ask about any health & safety related queries
Asankhaya Sharma PRO
codelion
AI & ML interests
Creator of OptiLLM, OpenEvolve, Adaptive Classifier, and Ellora. Pioneering a new category in AI infrastructure: inference-time compute for LLMs.
Recent Activity
reacted
to
their
post
with 🤯
5 days ago
🚀 Adaptive Classifier v0.0.17 Released - Major Accuracy Improvements!
We've just released a major update fixing critical bugs that were causing 40-50% accuracy drops in our enterprise classifiers!
Key Fixes:
• Fixed k-parameter prediction bug causing massive accuracy loss
• Improved incremental learning for new classes
• Enhanced weight preservation during model updates
Dramatic Results:
• fraud-detection: 43.9% → 92.7% (+48.8%) https://huggingface.co/adaptive-classifier/fraud-detection
• business-sentiment: 88.9% → 98.8% (+9.9%) https://huggingface.co/adaptive-classifier/business-sentiment• expense-category: 26.7% → 84.2% (+57.5%)
https://huggingface.co/adaptive-classifier/expense-category
• language-detection: 98.8% → 100% (+1.2%) https://huggingface.co/adaptive-classifier/language-detection
15/17 enterprise classifiers now maintain ≤5% accuracy difference from original performance!
Other High-Performing Models:
• email-security (93.8%): https://huggingface.co/adaptive-classifier/email-security
• content-moderation (100%): https://huggingface.co/adaptive-classifier/content-moderation
• pii-detection (100%): https://huggingface.co/adaptive-classifier/pii-detection
Quick Start:
from adaptive_classifier import AdaptiveClassifier
classifier = AdaptiveClassifier.load("adaptive-classifier/fraud-detection")
predictions = classifier.predict("Suspicious transaction pattern", k=3)
Install: pip install --upgrade adaptive-classifier==0.0.17
All models: https://huggingface.co/adaptive-classifier
🎯 Production-ready continuous learning for enterprise text classification!
#MachineLearning #TextClassification #ContinualLearning #EnterpriseAI
reacted
to
their
post
with 🚀
5 days ago
🚀 Adaptive Classifier v0.0.17 Released - Major Accuracy Improvements!
We've just released a major update fixing critical bugs that were causing 40-50% accuracy drops in our enterprise classifiers!
Key Fixes:
• Fixed k-parameter prediction bug causing massive accuracy loss
• Improved incremental learning for new classes
• Enhanced weight preservation during model updates
Dramatic Results:
• fraud-detection: 43.9% → 92.7% (+48.8%) https://huggingface.co/adaptive-classifier/fraud-detection
• business-sentiment: 88.9% → 98.8% (+9.9%) https://huggingface.co/adaptive-classifier/business-sentiment• expense-category: 26.7% → 84.2% (+57.5%)
https://huggingface.co/adaptive-classifier/expense-category
• language-detection: 98.8% → 100% (+1.2%) https://huggingface.co/adaptive-classifier/language-detection
15/17 enterprise classifiers now maintain ≤5% accuracy difference from original performance!
Other High-Performing Models:
• email-security (93.8%): https://huggingface.co/adaptive-classifier/email-security
• content-moderation (100%): https://huggingface.co/adaptive-classifier/content-moderation
• pii-detection (100%): https://huggingface.co/adaptive-classifier/pii-detection
Quick Start:
from adaptive_classifier import AdaptiveClassifier
classifier = AdaptiveClassifier.load("adaptive-classifier/fraud-detection")
predictions = classifier.predict("Suspicious transaction pattern", k=3)
Install: pip install --upgrade adaptive-classifier==0.0.17
All models: https://huggingface.co/adaptive-classifier
🎯 Production-ready continuous learning for enterprise text classification!
#MachineLearning #TextClassification #ContinualLearning #EnterpriseAI
reacted
to
their
post
with 🔥
5 days ago
🚀 Adaptive Classifier v0.0.17 Released - Major Accuracy Improvements!
We've just released a major update fixing critical bugs that were causing 40-50% accuracy drops in our enterprise classifiers!
Key Fixes:
• Fixed k-parameter prediction bug causing massive accuracy loss
• Improved incremental learning for new classes
• Enhanced weight preservation during model updates
Dramatic Results:
• fraud-detection: 43.9% → 92.7% (+48.8%) https://huggingface.co/adaptive-classifier/fraud-detection
• business-sentiment: 88.9% → 98.8% (+9.9%) https://huggingface.co/adaptive-classifier/business-sentiment• expense-category: 26.7% → 84.2% (+57.5%)
https://huggingface.co/adaptive-classifier/expense-category
• language-detection: 98.8% → 100% (+1.2%) https://huggingface.co/adaptive-classifier/language-detection
15/17 enterprise classifiers now maintain ≤5% accuracy difference from original performance!
Other High-Performing Models:
• email-security (93.8%): https://huggingface.co/adaptive-classifier/email-security
• content-moderation (100%): https://huggingface.co/adaptive-classifier/content-moderation
• pii-detection (100%): https://huggingface.co/adaptive-classifier/pii-detection
Quick Start:
from adaptive_classifier import AdaptiveClassifier
classifier = AdaptiveClassifier.load("adaptive-classifier/fraud-detection")
predictions = classifier.predict("Suspicious transaction pattern", k=3)
Install: pip install --upgrade adaptive-classifier==0.0.17
All models: https://huggingface.co/adaptive-classifier
🎯 Production-ready continuous learning for enterprise text classification!
#MachineLearning #TextClassification #ContinualLearning #EnterpriseAI
Organizations
