zerofata/G4-MeroMero-31B
LoRA-style vs google/gemma-4-31B-it. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 60 of 60 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, Norms 0/523, other 0/62, MLP 180/261, Attention 230/338
5 derivatives checked
- zerofata/G4-MeroMero-31B-gguf: Same weights, converted (fewer layers)
- mradermacher/G4-MeroMero-31B-i1-GGUF: Quantization (fewer layers)
- mradermacher/G4-MeroMero-31B-GGUF: Quantization (fewer layers)
- llmfan46/G4-MeroMero-31B-uncensored-heretic: Abliterated
- beezu/G4-MeroMero-31B-mlx-mxfp4: Quantization