🚀 i3-80M Text Generation

Powered by Mamba-based Architecture

Generate creative text using the i3-80M language model with customizable parameters.
10 500
0.1 2
1 100
💡 Try These Examples
✍️ Enter Your Prompt Max Tokens Temperature Top-k Sampling

Model Architecture:

  • Model: i3-80M
  • Device: cpu
  • Vocab Size: 41,320
  • Parameters: 82,765,160 (82.77M)

Configuration:

  • d_model: 512
  • n_heads: 16
  • max_seq_len: 256
  • d_state: 32

Built with ❤️ using Gradio | Model: FlameF0X/i3-80m