ermiaazarkhalili/LFM2-700M-GRPO-NuminaMath-10K-GGUF
Adapter vs ermiaazarkhalili/LFM2-700M-GRPO-NuminaMath-10K. ermiaazarkhalili/LFM2-700M-GRPO-NuminaMath-10K is a LoRA adapter, not full weights: rank 16, on k_proj, q_proj, v_proj in 6 layers (18 adapted matrices). It modifies ermiaazarkhalili/LFM2-700M-GRPO-NuminaMath-10K-GGUF at load time.