MuXodious/gemma-3n-E4B-it-absolute-heresy
Partial fine-tune vs google/gemma-3n-E4B-it. Partial change: 12% of the weights changed (attention, mlp, other), in 26 of 35 layers.
Tensors changed: Attention 8/363, Embeddings 0/25, Norms 0/489, other 3/687, MLP 26/112
4 derivatives checked
- mradermacher/gemma-3n-E4B-it-absolute-heresy-i1-GGUF: Quantization (fewer layers)
- mradermacher/gemma-3n-E4B-it-absolute-heresy-GGUF: Same weights, converted (fewer layers)
- MuXodious/gemma-3n-E4B-it-absolute-heresy-imatrix-GGUF: Quantization (fewer layers)
- MuXodious/gemma-3n-E4B-it-absolute-heresy-GGUF: Same weights, converted (fewer layers)