AI & ML interests

Knowledge Distillation, Self-Alignement

Recent Activity

distil-labs 's collections 4

distil-qwen3-4b-text2sql
A fine-tuned Qwen3-4B model for converting natural language questions into SQL queries. Trained using knowledge distillation from DeepSeek-V3, this 4B
PII Redaction
We trained and released a family of small language models (SLMs) specialized for policy-aware PII redaction.