KeeganCarey/gemma-3-1b-it-amr_thinking

GemmaThink-32k (GRPO Trained)

This model was trained using GRPO (Group Relative Policy Optimization) to generate structured reasoning traces.

Training Details

• Base Model: chimbiwide/gemma-3-1b-it-thinking-32k-sft-base
• Training Method: SFT + GRPO
• LoRA Rank: 32
• LoRA Alpha: 64.0
• Framework: Tunix (JAX)
• Hardware: v6e-1 TPU in Colab

Output Format

<reasoning>step-by-step thinking process</reasoning>
<answer>final answer</answer>

Quicklinks:

• SFT Base Model
• SFT Base Model Q8 GGUF
• GRPO Full Model <-- You're here
• Q8-GGUF
• Article