🤖 Stentor-12M: Compact Language Model Demo

A 12M parameter language model trained on educational content. Model Details:

  • 12M parameters
  • 512 token context
  • Trained in 1.3 hours on 2x T4 GPUs
  • Base model (no safety tuning)

Try it out with different prompts!
10 200
0.1 2
0.1 1
Examples
Prompt Max New Tokens Temperature Top P

About Stentor-12M

Stentor-12M is a compact, efficient language model built on the Llama architecture.

Links:

Note: This is a base model without safety alignment. Outputs may be unpredictable.