Nitral-Archive/MMRExCEV-GRPO-v0.420
Full fine-tune vs Nitral-AI/Captain-Eris_Violet-GRPO-v0.420. Fine-tune: 98% of the weights changed, across 40 of 40 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 43/81, MLP 117/120, Attention 156/160
2 derivatives checked
- mradermacher/MMRExCEV-GRPO-v0.420-i1-GGUF: Quantization
- mradermacher/MMRExCEV-GRPO-v0.420-GGUF: Quantization