A fine-tuned Qwen3-4B model for converting natural language questions into SQL queries. Trained using knowledge distillation from DeepSeek-V3, this 4B
distil labs
company
Verified
AI & ML interests
Knowledge Distillation, Self-Alignement
Recent Activity
A small function-calling git agent you can run locally
Gitara = git + ara (the parrot): your local stochastic parrot for git commands
We trained and released a family of small language models (SLMs) specialized for policy-aware PII redaction.
-
distil-labs/Distil-PII-Llama-3.2-1B-Instruct
Text Generation • 1B • Updated • 33 • 4 -
distil-labs/Distil-PII-SmolLM2-135M-Instruct-gguf
Text Generation • 0.1B • Updated • 39 -
distil-labs/Distil-PII-gemma-3-270m-it-gguf
Text Generation • 0.3B • Updated • 116 • 3 -
distil-labs/Distil-PII-gemma-3-270m-it
Text Generation • 0.3B • Updated • 17
A fine-tuned Qwen3-4B model for converting natural language questions into SQL queries. Trained using knowledge distillation from DeepSeek-V3, this 4B
A small function-calling git agent you can run locally
Gitara = git + ara (the parrot): your local stochastic parrot for git commands
We trained and released small language models for interacting with non-playable characters in games using natural language
We trained and released a family of small language models (SLMs) specialized for policy-aware PII redaction.
-
distil-labs/Distil-PII-Llama-3.2-1B-Instruct
Text Generation • 1B • Updated • 33 • 4 -
distil-labs/Distil-PII-SmolLM2-135M-Instruct-gguf
Text Generation • 0.1B • Updated • 39 -
distil-labs/Distil-PII-gemma-3-270m-it-gguf
Text Generation • 0.3B • Updated • 116 • 3 -
distil-labs/Distil-PII-gemma-3-270m-it
Text Generation • 0.3B • Updated • 17