MuXodious/gemma-3n-E4B-it-absolute-heresy-MPOA
Partial fine-tune vs google/gemma-3n-E4B-it. Partial change: 15% of the weights changed (attention, mlp, other), in 31 of 35 layers.
Tensors changed: Attention 28/363, Embeddings 0/25, Norms 0/489, other 3/687, MLP 31/112
4 derivatives checked
- MuXodious/gemma-3n-E4B-it-absolute-heresy-MPOA-GGUF: Same weights, converted (fewer layers)
- mradermacher/gemma-3n-E4B-it-absolute-heresy-MPOA-i1-GGUF: Quantization (fewer layers)
- MuXodious/gemma-3n-E4B-it-absolute-heresy-MPOA-imatrix-GGUF: Quantization (fewer layers)
- mradermacher/gemma-3n-E4B-it-absolute-heresy-MPOA-GGUF: Same weights, converted (fewer layers)
1 other repos hold byte-for-byte identical weight files.