Model Card for Model ID

fine tuned on facebook/natural_reasoning for 2.5K steps using 4bit quantization.

Evaluated using LightEval

Framework versions

  • Optimizer: AdaFactor
  • Bitsandbytes
  • PEFT 0.14.0
Downloads last month
15
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for chungimungi/4bit-Gemma3-1b-it-natural-reasoning-2500

Adapter
(95)
this model

Dataset used to train chungimungi/4bit-Gemma3-1b-it-natural-reasoning-2500

Collection including chungimungi/4bit-Gemma3-1b-it-natural-reasoning-2500